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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 119607
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to chemical properties and reactions

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

    steric hindrance

    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
     itſelf
    -0.67
    Amigo
    -0.63
    uxxxx
    -0.62
     Pfund
    -0.60
     Krone
    -0.58
     Einheit
    -0.58
     Lohn
    -0.56
     Beine
    -0.56
    Prova
    -0.55
     Segen
    -0.55
    POSITIVE LOGITS
    Tē
    0.56
     habet
    0.53
     shuts
    0.52
     iscri
    0.51
    chengla
    0.51
    смотра
    0.50
     ligiloj
    0.50
     Sar
    0.50
     {\
    0.49
     Bub
    0.49
    Activations Density 4.307%

    No Known Activations