© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4208
    Prev
    Next
    INDEX
    Explanations

    connections and relationships within complex systems

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

    Follows "of," "this," or "on."

    np_acts-logits-general · gemini-2.0-flash

    of this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.77
     Theſe
    -0.71
    principalColumn
    -0.68
    yntaxException
    -0.67
     ſind
    -0.65
    EDEFAULT
    -0.63
     snippetHide
    -0.63
    ournal
    -0.62
    ValueStyle
    -0.61
    wieś
    -0.61
    POSITIVE LOGITS
    的那个
    0.35
     the
    0.35
    IsMutable
    0.32
    這個
    0.32
    élaboration
    0.32
    这个
    0.30
     dicha
    0.30
     said
    0.28
     referido
    0.28
     mencionados
    0.27
    Activations Density 1.409%

    No Known Activations