Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129900
    Prev
    Next
    INDEX
    Explanations

    the presence of an opening parenthesis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.66
    Personendaten
    -0.64
    ArrowToggle
    -0.62
    OGND
    -0.60
    AutoScaleMode
    -0.59
    XmlAccessType
    -0.58
    ftagPool
    -0.58
     ModelExpression
    -0.54
    
    -0.54
    NameInMap
    -0.53
    POSITIVE LOGITS
     (-
    0.43
     carriers
    0.39
    绞
    0.38
     buruk
    0.38
     tersenyum
    0.36
     Potencia
    0.36
     الحره
    0.35
     partitions
    0.35
     Púb
    0.35
     foundry
    0.35
    Activations Density 0.000%

    No Known Activations