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. 130046
    Prev
    Next
    INDEX
    Explanations

    references to scientific papers and publications

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

    years and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     satunya
    -0.48
    CLAIMER
    -0.46
     Méndez
    -0.42
    adə
    -0.41
    ConstraintMaker
    -0.40
     мәкал
    -0.39
    }})
    -0.38
     Kessler
    -0.37
    ไว้
    -0.37
     velvet
    -0.37
    POSITIVE LOGITS
     المعيارى
    0.60
     TextInputType
    0.54
     Walkover
    0.54
    AutoScaleMode
    0.52
    XmlAccessType
    0.50
     AttributeSet
    0.48
     OFDb
    0.45
    FunctionFlags
    0.45
    matchCondition
    0.44
     stanga
    0.43
    Activations Density 0.006%

    No Known Activations