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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 91495
    Prev
    Next
    INDEX
    Explanations

    programming and markup language syntax elements

    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
     disambiguazione
    -0.71
     estekak
    -0.69
    ########.
    -0.60
    下载附件
    -0.59
    complexType
    -0.58
    Cyfeiriadau
    -0.57
     transfieras
    -0.56
     ujednoznacz
    -0.56
     OMITBAD
    -0.55
    oredCriteria
    -0.54
    POSITIVE LOGITS
    httphttps
    0.44
    deinit
    0.38
     poffible
    0.38
    onek
    0.36
     Possible
    0.36
     Ostro
    0.35
     latar
    0.35
    viks
    0.35
    ResourceManager
    0.35
    ukin
    0.35
    Activations Density 0.132%

    No Known Activations