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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 70710
    Prev
    Next
    INDEX
    Explanations

    references to authority figures and their influence on societal norms and ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Words that appear in politically charged, ideological, or controversial discourse, often representing divisive concepts, beliefs, or positions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tracce
    -0.44
    matchCondition
    -0.39
    CppMethod
    -0.37
    ModelSerializer
    -0.37
    –¿
    -0.36
    poň
    -0.35
     peny
    -0.35
    bayan
    -0.34
    ристання
    -0.34
    myself
    -0.34
    POSITIVE LOGITS
    verwijspagina
    0.54
    queryInterface
    0.47
    InstrumentedTest
    0.43
     BERNAMA
    0.41
     defaultstate
    0.40
    ViewFeatures
    0.40
    cèse
    0.40
    reni
    0.39
    PyExc
    0.39
    lesias
    0.38
    Activations Density 0.132%

    No Known Activations