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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 11341
    Prev
    Next
    INDEX
    Explanations

    phrases that involve describing, discussing, and analyzing various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.71
    twimg
    -0.68
    ksikon
    -0.65
     BorderRadius
    -0.64
     Shakspeare
    -0.63
     estekak
    -0.63
     NDEBUG
    -0.61
     tartalomajánló
    -0.61
    SequentialGroup
    -0.58
     Majefty
    -0.58
    POSITIVE LOGITS
     how
    1.51
    how
    1.01
     cómo
    0.93
    How
    0.88
     bagaimana
    0.86
     hvordan
    0.83
     why
    0.82
     How
    0.82
     ways
    0.80
     كيف
    0.76
    Activations Density 0.613%

    No Known Activations