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. 1-GEMMASCOPE-RES-16K
    6. 9523
    Prev
    Next
    INDEX
    Explanations

    references to assistance or support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nette
    -0.56
     crom
    -0.55
    <eos>
    -0.53
     Rech
    -0.53
    fels
    -0.52
    Filmografie
    -0.52
    es
    -0.50
     People
    -0.50
    …………………………………………
    -0.50
     Lübeck
    -0.50
    POSITIVE LOGITS
     aid
    4.27
     Aid
    4.06
    Aid
    3.56
    aid
    3.29
     AID
    3.08
     aids
    2.99
    AID
    2.54
     Aids
    2.52
     aiding
    2.40
     aide
    2.36
    Activations Density 0.066%

    No Known Activations