© 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. 18-GEMMASCOPE-RES-16K
    11. 1673
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated patterns or structures

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

    Numerical data, often percentages or zero values

    np_acts-logits-general · gemini-2.0-flash

    lists of numbers with zeros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.82
    دانشنامهٔ
    -0.78
     tartalomajánló
    -0.77
    şiv
    -0.72
    <bos>
    -0.72
     Pristupljeno
    -0.71
     Wikimedijinoj
    -0.67
    AndroidJUnit
    -0.67
     VIAF
    -0.67
    wahati
    -0.66
    POSITIVE LOGITS
     المعيارى
    0.58
    ,
    0.52
     utafitiHapana
    0.52
     للاسماء
    0.51
     OMITTED
    0.49
    listFiles
    0.44
    fortawesome
    0.43
     وتسجيلات
    0.42
    autoconfigure
    0.41
    namental
    0.41
    Activations Density 0.272%

    No Known Activations