Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5144
    Prev
    Next
    INDEX
    Explanations

    references to studies or findings related to genetic pathways and their implications in various contexts

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

    Follows first-person pronouns ("I", "my")

    np_acts-logits-general · gemini-2.0-flash

    proof of the main theorem

    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
    LookAnd
    -1.08
    AccessorTable
    -1.04
    parsedMessage
    -1.01
    uxxxx
    -0.96
    MigrationBuilder
    -0.95
    OGND
    -0.93
    SharedDtor
    -0.93
    MemoryWarning
    -0.89
    IntoConstraints
    -0.88
     فريبيس
    -0.88
    POSITIVE LOGITS
    —
    0.50
    раздо
    0.43
     vache
    0.42
     giusti
    0.41
     viață
    0.40
     faptul
    0.39
     “
    0.39
    --
    0.39
    爲
    0.38
     keting
    0.38
    Activations Density 1.331%

    No Known Activations