© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14974
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming or data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ababa
    -0.60
    .*")]
    -0.58
    pshire
    -0.57
    +:+
    -0.57
    ühungen
    -0.56
     Utama
    -0.53
    hloromethane
    -0.52
     Prefeitura
    -0.51
    JKLM
    -0.50
    épaisseur
    -0.48
    POSITIVE LOGITS
     beginnetje
    0.79
    quias
    0.69
     mergeFrom
    0.67
     ComVisible
    0.64
    aarrggbb
    0.63
    Demografie
    0.60
    (@
    0.59
    Manbalar
    0.59
    gameserver
    0.58
    textAppearance
    0.57
    Activations Density 1.289%

    No Known Activations