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. 6105
    Prev
    Next
    INDEX
    Explanations

    paths and identifiers related to events and applications

    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
    Rujuakan
    -0.99
    bootstrapcdn
    -0.95
     raiſ
    -0.95
     itſelf
    -0.89
     himſelf
    -0.88
     Jefus
    -0.87
    PreferredItem
    -0.87
     Reſ
    -0.87
     uſed
    -0.86
     themſelves
    -0.86
    POSITIVE LOGITS
     sources
    0.54
     Sources
    0.50
    sources
    0.47
    ällor
    0.46
    gemeinde
    0.46
     Source
    0.46
     SOURCE
    0.45
    Sources
    0.44
     paling
    0.43
    ALPHA
    0.43
    Activations Density 0.194%

    No Known Activations