© 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. 10610
    Prev
    Next
    INDEX
    Explanations

    a combination of context-specific words and phrases related to numerical values and their classifications

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

    Followed by a question mark

    np_acts-logits-general · gemini-2.0-flash

    questions about facts and numbers

    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
    .";
    -1.22
    '],
    -1.17
    .");
    -1.14
    '),
    -1.13
    .",
    -1.11
    .")
    -1.11
    "])
    -1.10
    "];
    -1.10
    '];
    -1.10
    "]);
    -1.09
    POSITIVE LOGITS
     المعرف
    0.47
    0.42
    ">
    0.41
    ApiProperty
    0.40
    MENAFN
    0.40
    gène
    0.40
    ГЛА
    0.39
    ;
    0.39
     awakeFromNib
    0.39
    Dtor
    0.37
    Activations Density 0.316%

    No Known Activations