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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7352
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and server operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stateMutability
    -0.35
    careous
    -0.35
     imageNamed
    -0.32
    SPO
    -0.31
    Према
    -0.31
    Anglo
    -0.30
     Eh
    -0.30
    SourceChecksum
    -0.30
     chi̍t
    -0.30
    ItemStack
    -0.29
    POSITIVE LOGITS
    ValueStyle
    0.56
    ír
    0.55
     CURIAM
    0.54
    ir
    0.52
    Personendaten
    0.51
    IRE
    0.50
     nahilalakip
    0.49
    WriteTagHelper
    0.48
    idos
    0.47
     Италијани
    0.47
    Activations Density 0.354%

    No Known Activations