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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 1962
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court rulings and legal codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fors
    -0.45
    刮
    -0.43
     mon
    -0.42
     ici
    -0.42
    }],
    
    -0.41
     here
    -0.40
     estrat
    -0.40
     enda
    -0.40
     multi
    -0.40
     principal
    -0.40
    POSITIVE LOGITS
    MigrationBuilder
    1.27
     AttributeSet
    1.00
    LookAnd
    0.90
     NSCoder
    0.84
    KommentareTeilen
    0.83
     disambiguazione
    0.83
    djangoproject
    0.83
     חיצוניים
    0.82
     onCreateView
    0.81
    VIAF
    0.81
    Activations Density 0.753%

    No Known Activations