© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 6434
    Prev
    Next
    INDEX
    Explanations

    terms related to conditional models and robustness in statistical methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical or academic adverbs and adjectives (particularly those ending in "-ly" or describing methodology, scope, or distribution in scientific contexts).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    technical methodological qualifiers that describe conditions, scope, structure, or modality in scientific/computational texts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Conclusión
    -0.40
    ToDelete
    -0.37
     great
    -0.33
     things
    -0.32
     Hochsch
    -0.32
     nejak
    -0.31
    Conclusion
    -0.31
    PrintStream
    -0.31
     lovely
    -0.31
     Schluß
    -0.30
    POSITIVE LOGITS
    uxxxx
    0.90
    findpost
    0.86
     للاسماء
    0.85
    GEBURTSDATUM
    0.82
     мәкал
    0.82
    ftagPool
    0.82
    Personendaten
    0.82
     BoxFit
    0.81
    httphttps
    0.81
    InjectAttribute
    0.79
    Activations Density 1.943%

    No Known Activations