© 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. 15736
    Prev
    Next
    INDEX
    Explanations

    syntax related to function and method definitions in programming code

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

    Follows "const" (or comma/parenthesis)

    np_acts-logits-general · gemini-2.0-flash

    constants and code declarations

    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
    SequentialGroup
    -0.69
    whether
    -0.58
    devamını
    -0.56
    });*/
    -0.55
    })*/
    -0.54
     thing
    -0.53
     THING
    -0.52
     localObject
    -0.52
     ligiloj
    -0.52
    thing
    -0.50
    POSITIVE LOGITS
    const
    2.73
     const
    2.47
    Const
    1.16
     Const
    1.14
     consta
    1.08
     constriction
    1.03
     constable
    0.95
     constante
    0.94
     constantes
    0.90
    CONST
    0.87
    Activations Density 0.063%

    No Known Activations