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. 25-GEMMASCOPE-RES-16K
    6. 215
    Prev
    Next
    INDEX
    Explanations

    phrases related to administrative procedures for obtaining documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nargin
    -0.59
    WriteLiteral
    -0.56
    antMatchers
    -0.53
    gatsby
    -0.52
    Fandom
    -0.52
    ERMIN
    -0.51
    참고
    -0.50
     bezeichneter
    -0.49
    Politique
    -0.49
    ậy
    -0.49
    POSITIVE LOGITS
     particulars
    0.63
    timation
    0.63
     Signalez
    0.61
     duly
    0.60
     SOFT
    0.60
     AssemblyCulture
    0.59
    脚注の使い方
    0.57
     soft
    0.57
     Chall
    0.56
    Nationalité
    0.56
    Activations Density 0.098%

    No Known Activations