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. 21-GEMMASCOPE-RES-16K
    6. 7400
    Prev
    Next
    INDEX
    Explanations

    references to organizations and authority figures involved in various sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.60
    ISupport
    -0.58
    djangoproject
    -0.57
     Hermans
    -0.55
    BeginContext
    -0.54
     تانيه
    -0.54
    árol
    -0.54
    Pratique
    -0.53
    Datuak
    -0.52
    luiting
    -0.52
    POSITIVE LOGITS
     responsible
    2.18
     charge
    2.12
     charged
    2.05
     tasked
    1.92
    responsible
    1.90
    charge
    1.76
     Charge
    1.69
     Responsible
    1.68
    Responsible
    1.64
     Charged
    1.60
    Activations Density 0.382%

    No Known Activations