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. 6-GEMMASCOPE-RES-16K
    6. 5221
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistics and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    étape
    -0.66
     useParams
    -0.56
    quelles
    -0.55
     berta
    -0.54
     Zep
    -0.51
    CLUD
    -0.51
    atoma
    -0.50
    vités
    -0.50
     Constitucional
    -0.49
    troppo
    -0.48
    POSITIVE LOGITS
     resourceCulture
    0.85
    featureID
    0.75
    AutoScaleMode
    0.67
     surla
    0.66
    AndEndTag
    0.66
    tagext
    0.66
    WithIOException
    0.61
     Pristupljeno
    0.59
     transfieras
    0.59
    )$/,
    0.58
    Activations Density 0.353%

    No Known Activations