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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3797
    Prev
    Next
    INDEX
    Explanations

    concepts related to the value of human life and personal worth

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

    phrases emphasizing human value, empowerment, and collective strength.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    clusal
    -0.56
    LookAnd
    -0.53
     iprot
    -0.50
    matchCondition
    -0.47
     meia
    -0.45
     tensão
    -0.45
    +#+#
    -0.44
     calculate
    -0.44
     فريبيس
    -0.43
     sorely
    -0.43
    POSITIVE LOGITS
    новништво
    0.48
     تضيفلها
    0.44
    pushFollow
    0.41
     everyone
    0.40
    AutoField
    0.39
    belong
    0.36
    belongs
    0.36
     Würde
    0.35
    tagHelperRunner
    0.35
    everyone
    0.35
    Activations Density 0.143%

    No Known Activations