© 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. 18-GEMMASCOPE-RES-16K
    11. 8911
    Prev
    Next
    INDEX
    Explanations

    phrases that reference specific parts or sections of a larger context

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

    "of the"

    np_acts-logits-general · gemini-2.0-flash

    parts of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.87
     متعلقه
    -0.83
    المناصب
    -0.82
     يتيمه
    -0.81
     wireType
    -0.74
    ArgsConstructor
    -0.73
    harusnya
    -0.69
     downvotes
    -0.68
     atheists
    -0.68
     الحره
    -0.66
    POSITIVE LOGITS
     the
    0.68
     it
    0.55
     our
    0.55
     society
    0.52
     their
    0.50
     transfieras
    0.48
    ++){
    0.47
     [
    0.47
     her
    0.46
     life
    0.45
    Activations Density 0.269%

    No Known Activations