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. 10-GEMMASCOPE-RES-16K
    6. 11572
    Prev
    Next
    INDEX
    Explanations

    expressions of personal pride and identity as a single parent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.93
     disambiguazione
    -0.80
     gyhoeddwyd
    -0.71
    AddTagHelper
    -0.67
    WriteTagHelper
    -0.63
    abestanden
    -0.62
     ModelExpression
    -0.61
    GeneratedValue
    -0.60
    ("]");
    -0.59
     protoimpl
    -0.59
    POSITIVE LOGITS
     daily
    0.85
     regularly
    0.73
     weekly
    0.72
    daily
    0.70
     routinely
    0.69
     currently
    0.68
     nowadays
    0.64
     quotidien
    0.64
     nightly
    0.61
     monthly
    0.61
    Activations Density 0.529%

    No Known Activations