© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13378
    Prev
    Next
    INDEX
    Explanations

    terms and phrases indicating possession or collective ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.81
    ftagPool
    -0.77
     queſto
    -0.71
    Tembelea
    -0.68
     &___
    -0.68
    <unused52>
    -0.68
    <unused14>
    -0.67
    <unused8>
    -0.67
    [@BOS@]
    -0.67
    <unused16>
    -0.67
    POSITIVE LOGITS
     or
    0.43
     and
    0.33
    和
    0.31
     coroa
    0.31
     و
    0.31
     OR
    0.31
     to
    0.30
     be
    0.30
     not
    0.29
     vs
    0.29
    Activations Density 0.610%

    No Known Activations