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
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5271
    Prev
    Next
    INDEX
    Explanations

    references to individual experiences and opinions in a social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.65
     nahilalakip
    -0.64
     *)__
    -0.52
    /*---
    -0.49
    rrggbb
    -0.49
    Personendaten
    -0.48
     Италијани
    -0.46
    Diweddarwch
    -0.46
     चीज़ों
    -0.46
     trés
    -0.45
    POSITIVE LOGITS
     aDecoder
    0.41
     habit
    0.36
    istoitu
    0.34
    outSlope
    0.33
     decency
    0.33
    ंदीखरीदारी
    0.33
    dafx
    0.33
    retudo
    0.32
     convergence
    0.31
     dissonance
    0.31
    Activations Density 0.195%

    No Known Activations