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. 16-GEMMASCOPE-RES-16K
    6. 14871
    Prev
    Next
    INDEX
    Explanations

    programming-related commands or functions

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

    Code, references, and technical terms

    np_acts-logits-general · gemini-2.0-flash

    Q/A conversational context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.50
    PathVariable
    -0.49
    ();*/
    -0.47
    .”
    -0.47
    ,”
    -0.47
     */}
    -0.46
     consultato
    -0.46
    KommentareTeilen
    -0.44
     Heaton
    -0.42
    =’
    -0.42
    POSITIVE LOGITS
    <code>
    0.75
    Bbb
    0.72
     estekak
    0.70
     Normdatei
    0.69
    billon
    0.64
     ostavi
    0.63
    henge
    0.63
    şiv
    0.60
    lapsingToolbar
    0.60
     referenties
    0.60
    Activations Density 0.301%

    No Known Activations