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. 3-GEMMASCOPE-RES-16K
    6. 16339
    Prev
    Next
    INDEX
    Explanations

    specific terms and references related to legal and technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Davison
    -0.97
    dron
    -0.87
     Leon
    -0.86
     filepath
    -0.80
    LEON
    -0.79
    onimo
    -0.79
    jména
    -0.77
     Denton
    -0.76
    mtable
    -0.75
    Leon
    -0.75
    POSITIVE LOGITS
    بوابة
    0.88
     Prieto
    0.86
    toCharArray
    0.85
     Hodg
    0.85
    autorest
    0.85
     réguli
    0.85
    ContentAlignment
    0.84
    примеча
    0.84
     Phry
    0.84
     Kimmel
    0.82
    Activations Density 1.616%

    No Known Activations