© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8561
    Prev
    Next
    INDEX
    Explanations

    emotional responses and surprises in various contexts

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

    surprise or shock

    np_acts-logits-general · gemini-2.0-flash

    shocked or surprise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.57
     "]";
    -0.55
    Distribuzione
    -0.53
    __':
    -0.52
     makeStyles
    -0.52
    processable
    -0.51
    Portály
    -0.51
    quema
    -0.51
     ContentValues
    -0.49
    GrantedAuthority
    -0.49
    POSITIVE LOGITS
     surprise
    2.06
     unexpected
    2.04
     sudden
    1.90
     unexpectedly
    1.90
     suddenly
    1.85
    unexpected
    1.79
     surprises
    1.75
     Surprise
    1.72
    Surprise
    1.71
     Unexpected
    1.69
    Activations Density 0.277%

    No Known Activations