© 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. 25-GEMMASCOPE-RES-16K
    6. 2525
    Prev
    Next
    INDEX
    Explanations

    expressions of varying perspectives and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cref
    -0.61
     segala
    -0.55
     مشين
    -0.53
    HideFlags
    -0.53
    ########.
    -0.53
    XmlType
    -0.51
     TextAppearance
    -0.50
    gdx
    -0.50
    Relevant
    -0.49
     AssemblyTitle
    -0.49
    POSITIVE LOGITS
     others
    3.51
     Others
    3.19
    Others
    3.10
    others
    2.99
     OTHERS
    2.59
    OTHERS
    1.71
     some
    1.48
     otros
    1.42
     altri
    1.36
     دیگران
    1.32
    Activations Density 0.360%

    No Known Activations