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. 23-GEMMASCOPE-RES-131K
    6. 61
    Prev
    Next
    INDEX
    Explanations

    structured data formats and syntax elements, particularly related to collections or lists

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.60
    onAttach
    -0.50
     Réponses
    -0.49
    Kjelder
    -0.47
    ंदीखरीदारी
    -0.45
    Cyfeiriadau
    -0.44
     queſta
    -0.42
    RTLR
    -0.42
    VGND
    -0.41
    ]")]
    -0.40
    POSITIVE LOGITS
    LookAnd
    0.47
     Administrativna
    0.46
     propOrder
    0.46
    UrlResolution
    0.43
     جغرافيا
    0.42
    ConstraintMaker
    0.41
    Dış
    0.39
    PullParser
    0.39
    HideFlags
    0.39
    estimm
    0.38
    Activations Density 0.108%

    No Known Activations