Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12810
    Prev
    Next
    INDEX
    Explanations

    data types commonly used in programming languages, particularly those related to C and C++ syntax

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

    C/C++ type declarations

    np_acts-logits-general · gemini-2.0-flash

    casting to char* or int

    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
     ?>>
    -0.61
    hoeddwyd
    -0.59
     nakalista
    -0.58
    .):
    -0.57
     *);
    -0.57
     disambiguazione
    -0.55
    日閲覧
    -0.55
    ))->
    -0.53
    +;
    -0.53
    %),
    -0.53
    POSITIVE LOGITS
    )((
    0.77
    )(
    0.75
    )(((
    0.66
    }(
    0.63
    >(
    0.56
    ",(
    0.54
    ((
    0.53
     (*)
    0.52
    InteropServices
    0.52
    *)((
    0.51
    Activations Density 0.080%

    No Known Activations