© 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. 14352
    Prev
    Next
    INDEX
    Explanations

    code structure and object-oriented programming concepts

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

    Code snippets, XML, and data structures

    np_acts-logits-general · gemini-2.0-flash

    field group ResourceGroup

    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
     Савезне
    -0.75
     Tops
    -0.73
     Arenas
    -0.72
     Италијани
    -0.71
     Fields
    -0.69
     Turns
    -0.68
     Marks
    -0.68
     disambiguazione
    -0.68
     nakalista
    -0.68
     חיצוניים
    -0.67
    POSITIVE LOGITS
    <unused63>
    0.54
    <unused61>
    0.53
    <unused62>
    0.52
    <unused60>
    0.42
     diffe
    0.39
    )</
    0.39
    Hair
    0.37
     ancianos
    0.36
    "?>
    0.35
    ...")
    0.35
    Activations Density 0.107%

    No Known Activations