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. 1261
    Prev
    Next
    INDEX
    Explanations

    references to different types of events, organizations, or entities related to projects and their documentation

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

    Totals, counts, or quantities

    np_acts-logits-general · gemini-2.0-flash

    counts of entities

    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
     AssemblyCulture
    -0.67
    WithIOException
    -0.64
    ItemBackground
    -0.61
    protoimpl
    -0.60
     везе
    -0.56
    inheritdoc
    -0.54
    WebVitals
    -0.54
    NameInMap
    -0.53
     länge
    -0.53
    jsonwebtoken
    -0.52
    POSITIVE LOGITS
    Including
    0.76
     totalt
    0.76
     total
    0.74
     comples
    0.73
     including
    0.73
     Including
    0.71
     assorted
    0.69
     cumul
    0.68
     various
    0.68
     cumulative
    0.68
    Activations Density 0.443%

    No Known Activations