© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8708
    Prev
    Next
    INDEX
    Explanations

    snippets of code or command-line instructions related to SSH and scripting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arangay
    -0.76
    ſicht
    -0.75
    ſſung
    -0.72
    <unused68>
    -0.72
    <unused42>
    -0.72
    <unused14>
    -0.72
    <unused52>
    -0.71
    <unused74>
    -0.71
    [@BOS@]
    -0.71
    <unused8>
    -0.71
    POSITIVE LOGITS
    <eos>
    0.40
    {
    0.38
    setcounter
    0.32
     {
    0.31
    jątk
    0.31
     inmediata
    0.31
     Evangelio
    0.31
     ayudarte
    0.30
     aislada
    0.29
    It
    0.28
    Activations Density 3.037%

    No Known Activations