© 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. 8064
    Prev
    Next
    INDEX
    Explanations

    references to software updates and related documentation

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

    Code or symbols mixed with text

    np_acts-logits-general · gemini-2.0-flash

    YouTube 視 d 季 分

    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
     doubtnut
    -1.42
     itſelf
    -1.39
     ་་
    -1.35
     myſelf
    -1.34
     moschino
    -1.28
     Reſ
    -1.27
     Anſ
    -1.23
     ―――――
    -1.23
     $_(
    -1.22
     Monfieur
    -1.21
    POSITIVE LOGITS
     
    0.91
     To
    0.67
     I
    0.66
     W
    0.66
     O
    0.65
     The
    0.65
     He
    0.65
     C
    0.65
     Se
    0.64
     y
    0.64
    Activations Density 0.181%

    No Known Activations