Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14675
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forRoot
    -0.37
    SupportActionBar
    -0.37
     onCreateView
    -0.35
     Hobson
    -0.34
    HasForeignKey
    -0.33
    ExtendWith
    -0.33
    ฟัง
    -0.32
    &__
    -0.32
     번째
    -0.32
     Horseshoe
    -0.31
    POSITIVE LOGITS
    e
    0.73
    s
    0.73
    eto
    0.52
    uxxxx
    0.52
    eer
    0.50
    eins
    0.50
    eti
    0.50
    eig
    0.50
    ScopeManager
    0.49
    i
    0.49
    Activations Density 0.368%

    No Known Activations