© 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. 22-GEMMASCOPE-RES-16K
    11. 15295
    Prev
    Next
    INDEX
    Explanations

    unexpected reactions and emotions related to news or events

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

    followed by variants of "surprise" or "shock"

    np_acts-logits-general · gemini-2.0-flash

    not surprising or surprising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.59
    Enlaces
    -0.58
     समीक्षाएं
    -0.55
    ArgsConstructor
    -0.55
    logrus
    -0.52
    Ссылки
    -0.51
     تانيه
    -0.51
     Parcelable
    -0.50
    umque
    -0.50
    indicato
    -0.49
    POSITIVE LOGITS
     surprise
    3.50
     surprised
    3.10
     surprises
    3.01
    surprise
    2.93
     Surprise
    2.87
    Surprise
    2.84
     surprising
    2.71
     shock
    2.63
    surprised
    2.59
     surpris
    2.46
    Activations Density 0.395%

    No Known Activations