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. 129915
    Prev
    Next
    INDEX
    Explanations

    opening and closing parentheses and brackets

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

    closing brackets `)`

    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
    商品説明
    -0.50
    حوالہ
    -0.50
    haikusbot
    -0.47
    >(_
    -0.47
    Manbalar
    -0.45
    ]");
    -0.45
     auseinander
    -0.45
    UnitTesting
    -0.45
    下载附件
    -0.44
    ]})
    -0.44
    POSITIVE LOGITS
    iNdEx
    0.44
    enumi
    0.42
    zzleHttp
    0.38
    ArgsConstructor
    0.38
     vectorielle
    0.37
     везе
    0.37
    AnchorStyles
    0.36
    :✨
    0.36
    ffindor
    0.36
     şal
    0.36
    Activations Density 0.004%

    No Known Activations