© 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. 4877
    Prev
    Next
    INDEX
    Explanations

    instances of the term "VW" or its variations in the text

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

    Volkswagen and appraisals

    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
    \{\\
    -0.65
     Hakim
    -0.59
     AssemblyCulture
    -0.59
     kaarangay
    -0.58
     незавершена
    -0.57
     تضيفلها
    -0.57
    fjspx
    -0.57
    bibfnamefont
    -0.57
    Personendaten
    -0.56
    ьаж
    -0.54
    POSITIVE LOGITS
    vw
    2.17
    VW
    1.72
     vw
    1.59
     VW
    1.53
    Vw
    1.13
     Volkswagen
    0.52
    uvw
    0.50
    view
    0.50
    Volkswagen
    0.49
    VIEW
    0.49
    Activations Density 0.002%

    No Known Activations