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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 22283
    Prev
    Next
    INDEX
    Explanations

    terms related to bipartite graphs and the bootstrapcdn resource

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

    Golden Globe nominations, bipartite graphs, bootstrap links

    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
    rungsseite
    -1.17
     disambiguazione
    -0.64
    باردا
    -0.57
     endblock
    -0.57
    الإنجليزية
    -0.57
    ロウィン
    -0.56
     Dieſe
    -0.54
     Weiſe
    -0.54
    wußt
    -0.53
     يتيمه
    -0.53
    POSITIVE LOGITS
    FindBy
    0.45
    findBy
    0.38
    findElement
    0.32
    by
    0.31
    oredCriteria
    0.31
    Hozzáférés
    0.31
    validates
    0.31
    annotation
    0.30
    obec
    0.29
    Schedulers
    0.29
    Activations Density 0.002%

    No Known Activations