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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113749
    Prev
    Next
    INDEX
    Explanations

    concepts related to storing and organizing fishing equipment and wires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.44
     Einfluß
    -0.41
    OGND
    -0.40
    ftagPool
    -0.40
     Empieza
    -0.39
    SequentialGroup
    -0.39
    indung
    -0.39
    "}")
    -0.37
    bürger
    -0.37
    SerializeField
    -0.37
    POSITIVE LOGITS
    adaptiveStyles
    0.48
     Bias
    0.43
    WebElementEntity
    0.42
    供
    0.40
     Streak
    0.40
    thmetic
    0.40
     folded
    0.39
    scriptId
    0.39
    rinos
    0.38
     holster
    0.38
    Activations Density 0.046%

    No Known Activations