© 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. 14404
    Prev
    Next
    INDEX
    Explanations

    references to secrets and hidden truths

    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
    isiaj
    -0.46
    Probably
    -0.43
     Probably
    -0.42
    PreExecute
    -0.42
     Rejo
    -0.41
    idać
    -0.40
    哭了
    -0.39
     Consistent
    -0.39
     Directly
    -0.39
     probably
    -0.38
    POSITIVE LOGITS
     secrets
    0.74
     unwittingly
    0.71
     mysterious
    0.71
     discovers
    0.66
     accidentally
    0.66
    rungsseite
    0.65
     secret
    0.65
     unexpectedly
    0.64
     '\\;'
    0.64
     mysteriously
    0.63
    Activations Density 0.635%

    No Known Activations