© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 82694
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation related to functions and their derivatives

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

    closing brace followed by other characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !
    -0.43
    .
    -0.40
    )
    -0.38
     I
    -0.37
    es
    -0.36
     experience
    -0.35
     play
    -0.34
    έ
    -0.33
     hidrá
    -0.33
     speed
    -0.33
    POSITIVE LOGITS
    }(
    1.52
     }}(
    1.20
    }}(
    1.19
    )}(
    1.13
     }(
    1.13
    .}(
    1.07
    >(
    1.03
     $(
    1.03
    ^{*}(
    1.03
    」(
    0.94
    Activations Density 0.087%

    No Known Activations