© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 121672
    Prev
    Next
    INDEX
    Explanations

    comments or annotations in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    rem before Filename, URL, sleep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.65
     pleaſure
    -0.60
    AndEndTag
    -0.58
     Poehler
    -0.57
     Chwiliwch
    -0.57
     Rodolfo
    -0.56
    casian
    -0.54
    ſelf
    -0.54
     MatDialog
    -0.53
    neurial
    -0.53
    POSITIVE LOGITS
    rem
    2.28
     rem
    2.11
     Rem
    2.06
    Rem
    1.98
    REM
    1.89
     REM
    1.85
     remo
    1.02
     Remo
    0.99
     Remy
    0.97
    remo
    0.96
    Activations Density 0.005%

    No Known Activations