© 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. 1-GEMMASCOPE-RES-16K
    11. 7307
    Prev
    Next
    INDEX
    Explanations

    patterns related to mathematical or logical expressions, particularly those involving parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (
    -1.46
     (
    -1.27
    [
    -1.25
    _
    -1.10
    1
    -1.10
     [
    -1.07
    -
    -1.05
    2
    -1.04
    '
    -1.04
    n
    -1.01
    POSITIVE LOGITS
    "])
    4.06
    ")));
    4.06
    ']))
    3.95
    )");
    3.83
    "]);
    3.81
    })$}
    3.81
    ')")
    3.79
    .)}
    3.78
    "]));
    3.78
    '))
    3.69
    Activations Density 0.535%

    No Known Activations