© 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. 35-GEMMASCOPE-RES-16K
    6. 14311
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific end-related terms and phrases

    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
    MERCE
    -0.40
    AddressBook
    -0.40
    hyrchwyd
    -0.40
    Clik
    -0.38
    mouseX
    -0.37
     '\\;'
    -0.37
    GHIJKLM
    -0.37
    ↹
    -0.37
    cristo
    -0.36
    itecture
    -0.36
    POSITIVE LOGITS
     End
    0.74
    End
    0.68
     Endgame
    0.64
    ToEnd
    0.63
     END
    0.60
    orses
    0.59
    setEnd
    0.59
     end
    0.57
    🔚
    0.56
    getEnd
    0.56
    Activations Density 0.183%

    No Known Activations