© 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. 3635
    Prev
    Next
    INDEX
    Explanations

    references to identifying or highlighting information

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

    preceding "out" or forms of "point"

    np_acts-logits-general · gemini-2.0-flash

    pointing out or directing towards

    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
    ⓘ
    -0.63
    ftagPool
    -0.59
    bootstrapcdn
    -0.56
     Вікіпе
    -0.54
    XmlEnum
    -0.53
    IContainer
    -0.52
     Sentiment
    -0.52
    évaluateur
    -0.52
    fortawesome
    -0.51
    JsonInclude
    -0.49
    POSITIVE LOGITS
     fingers
    0.97
     finger
    0.87
     pointed
    0.77
    fingers
    0.75
    finger
    0.74
     către
    0.72
     towards
    0.72
     toward
    0.70
     pointing
    0.70
    脚注の使い方
    0.67
    Activations Density 0.071%

    No Known Activations