© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8793
    Prev
    Next
    INDEX
    Explanations

    terms related to community involvement and leadership

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

    gendered pronouns and references to male/female distinctions using "his/her" constructions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yoksa
    -0.49
     bowiem
    -0.47
     nemlig
    -0.44
    __':
    -0.40
    verständlich
    -0.40
     namelijk
    -0.38
     totiž
    -0.38
    følgelig
    -0.36
     nämlich
    -0.36
     оригіналу
    -0.36
    POSITIVE LOGITS
    /
    2.52
     /
    1.75
    -/
    1.48
    ／
    1.48
    ()/
    1.41
    "/"
    1.30
    /(
    1.27
    /"
    1.25
    ./
    1.25
    /-
    1.23
    Activations Density 2.060%

    No Known Activations