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. 1277
    Prev
    Next
    INDEX
    Explanations

    specific frameworks, programming concepts, and technical specifications

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

    Questions about what or which

    np_acts-logits-general · gemini-2.0-flash

    questions are on-topic

    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
    modb
    -0.71
    Portale
    -0.58
    titleMargin
    -0.57
    Rüyada
    -0.57
     volando
    -0.56
     őket
    -0.55
    MigrationBuilder
    -0.55
    anah
    -0.53
    hnia
    -0.53
    AnimationsModule
    -0.53
    POSITIVE LOGITS
     would
    0.71
     we
    0.68
    ?».
    0.68
     you
    0.63
     they
    0.61
     are
    0.60
     can
    0.59
     has
    0.56
    ?')
    0.56
    ?</
    0.55
    Activations Density 0.126%

    No Known Activations