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. 0-GEMMASCOPE-RES-16K
    6. 9404
    Prev
    Next
    INDEX
    Explanations

    terms related to the notion of reference or consideration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aik
    -0.57
    元
    -0.56
    U
    -0.55
    g
    -0.55
    k
    -0.55
    enter
    -0.55
    on
    -0.53
    л
    -0.53
    J
    -0.53
    (
    -0.53
    POSITIVE LOGITS
    tvguidetime
    1.08
    BufferException
    1.05
     الرياضيه
    1.00
    StructEnd
    0.98
     defStyle
    0.98
    VersionUID
    0.97
     itſelf
    0.97
     Regard
    0.97
     Efq
    0.96
    InjectAttribute
    0.95
    Activations Density 0.128%

    No Known Activations