© 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. 7989
    Prev
    Next
    INDEX
    Explanations

    references to structured groups and classifications

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

    Followed by descriptions of a group, team or system

    np_acts-logits-general · gemini-2.0-flash

    comprising groups and their components

    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
    出版年
    -0.72
    Tikang
    -0.67
     Biôgrafia
    -0.60
    ترة
    -0.52
    TemporalType
    -0.50
     fidu
    -0.49
    ыгана
    -0.45
    paramref
    -0.45
    ATCC
    -0.45
    يسة
    -0.45
    POSITIVE LOGITS
     consisting
    2.93
     composed
    2.91
     comprised
    2.81
     comprising
    2.63
    composed
    2.47
     consists
    2.41
     Composed
    2.38
     consisted
    2.29
     composé
    2.25
     comprises
    2.24
    Activations Density 0.880%

    No Known Activations