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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 29654
    Prev
    Next
    INDEX
    Explanations

    references to personal or collective experiences

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

    lists of details or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    AccessorTable
    -0.50
    CROSSTALK
    -0.46
     Wikiseite
    -0.35
    นั้น
    -0.33
     memang
    -0.33
     sachant
    -0.33
     musst
    -0.32
    EDEFAULT
    -0.32
     Administrativna
    -0.32
     choć
    -0.31
    POSITIVE LOGITS
    RegistryLite
    0.55
    rungsseite
    0.50
     FormData
    0.49
    iania
    0.48
    tences
    0.47
     nomination
    0.47
     imagui
    0.47
    ils
    0.47
     nominations
    0.47
     Johnnie
    0.47
    Activations Density 0.084%

    No Known Activations