© 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. 7976
    Prev
    Next
    INDEX
    Explanations

    specific programming or data manipulation commands

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

    Code snippets or matrix/array indexing

    np_acts-logits-general · gemini-2.0-flash

    `][` after numbers or words

    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
    ($
    -1.13
    (");
    -1.13
    ()));
    -1.12
    ()]);
    -1.11
    (")
    -1.11
    ()]
    -1.10
    ()}
    -1.09
    ())));
    -1.07
    ('
    -1.06
    ()));
    -1.06
    POSITIVE LOGITS
    glGen
    0.51
    ][
    0.50
     tiguan
    0.48
     band
    0.46
    intios
    0.46
    band
    0.44
     opérés
    0.44
     amor
    0.43
    InputBorder
    0.42
     haue
    0.41
    Activations Density 0.254%

    No Known Activations