© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3781
    Prev
    Next
    INDEX
    Explanations

    concepts related to survival and escape from various dangers or challenges

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

    phrases describing escaping from danger or threats.

    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
     surla
    -0.83
     disambiguazione
    -0.77
    rungsseite
    -0.77
     صوتيه
    -0.77
    ftagPool
    -0.70
    ArgsConstructor
    -0.67
    enterOuterAlt
    -0.66
    ineno
    -0.66
    LayoutStyle
    -0.63
    GEBURTSDATUM
    -0.61
    POSITIVE LOGITS
     onslaught
    0.81
     scrutiny
    0.66
     criticism
    0.66
     adversity
    0.66
     attacks
    0.65
     pressures
    0.63
     threats
    0.62
     challenges
    0.62
     dangers
    0.60
     pressure
    0.57
    Activations Density 0.496%

    No Known Activations