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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43440
    Prev
    Next
    INDEX
    Explanations

    terms related to evaluation and assessment 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 @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.07
    parsedMessage
    -0.87
    twimg
    -0.86
    !*\
    -0.84
    IsContent
    -0.82
    GraphicsUnit
    -0.81
    脚注の使い方
    -0.81
    EndContext
    -0.74
     <=",
    -0.74
     ExecuteAsync
    -0.73
    POSITIVE LOGITS
     close
    0.49
    oo
    0.45
    reactivex
    0.42
     cos
    0.41
    mento
    0.41
    ccin
    0.40
     vitamin
    0.40
     alternatively
    0.40
    DispatchToProps
    0.40
     Emp
    0.40
    Activations Density 0.135%

    No Known Activations