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. 852
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to academic positions

    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
    OGND
    -0.65
    toHave
    -0.57
    Geografía
    -0.57
    Pfalz
    -0.55
    einander
    -0.54
    ConstraintMaker
    -0.54
    LITERAL
    -0.54
    grown
    -0.54
    yim
    -0.54
     Rhapsody
    -0.54
    POSITIVE LOGITS
     emeritus
    0.74
     Emeritus
    0.64
    Tikang
    0.64
    таратура
    0.60
    forName
    0.58
     universitarios
    0.55
     universitario
    0.54
    unknownFields
    0.53
     disambiguazione
    0.52
     \%$\\
    0.51
    Activations Density 0.031%

    No Known Activations