Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 9809
    Prev
    Next
    INDEX
    Explanations

    action verbs that indicate movement or significant activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Casey
    -0.73
    ressi
    -0.73
    </h1>
    -0.72
     Meksiku
    -0.71
    .$$
    -0.70
     Ehrlich
    -0.69
    </s>
    -0.69
    combe
    -0.69
     intermediate
    -0.68
     piemē
    -0.67
    POSITIVE LOGITS
     Went
    1.14
     Gave
    1.10
     Took
    1.10
    took
    1.09
     ran
    1.08
    Went
    1.07
     saw
    1.06
     Came
    1.04
    wrote
    1.03
    Gave
    1.03
    Activations Density 0.174%

    No Known Activations