© 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. 13805
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and numerical information related to statistics or measurements

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

    Percentages and numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and years

    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
    StandardCharsets
    -0.69
    TargetException
    -0.68
    ########.
    -0.68
    stdc
    -0.65
    CppCodeGen
    -0.60
    DrawerToggle
    -0.59
    EndGlobalSection
    -0.58
    DataBinding
    -0.58
    LayoutStyle
    -0.57
    下载附件
    -0.57
    POSITIVE LOGITS
    2
    0.85
     twenty
    0.84
     Twenty
    0.77
    Twenty
    0.71
    twenty
    0.65
    二十
    0.62
     TWENTY
    0.62
     thirty
    0.56
     vingt
    0.56
     eighteen
    0.56
    Activations Density 0.443%

    No Known Activations