© 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. 35-GEMMASCOPE-RES-16K
    11. 12668
    Prev
    Next
    INDEX
    Explanations

    conditional phrases related to programming and data manipulation

    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
     participado
    -0.57
     vivent
    -0.53
     comparten
    -0.50
     escuchado
    -0.50
     niega
    -0.49
     officiels
    -0.49
     naudoti
    -0.49
     découver
    -0.49
     savent
    -0.48
     habrá
    -0.48
    POSITIVE LOGITS
    Gön
    0.51
    HomeAsUpEnabled
    0.51
    Personensuche
    0.51
    MessageState
    0.50
     ProtoMessage
    0.50
     neutral
    0.49
    WithIOException
    0.48
    DockStyle
    0.47
     decl
    0.47
     dil
    0.47
    Activations Density 0.111%

    No Known Activations