© 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. 1588
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate issues, questions, and potential problems in various contexts

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

    Follows "question" or "problem"

    np_acts-logits-general · gemini-2.0-flash

    question/problem/option/feature is

    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
     OFDb
    -0.71
     محفوظة
    -0.69
     Efq
    -0.68
    MigrationBuilder
    -0.67
    ruptedException
    -0.64
     Waray
    -0.64
     Majefty
    -0.64
     joaat
    -0.63
     Shakspeare
    -0.63
    '}}>
    -0.60
    POSITIVE LOGITS
    AlterField
    0.64
     I
    0.60
     that
    0.59
    Voci
    0.50
     —
    0.48
     worth
    0.45
     we
    0.45
    ָד
    0.45
     note
    0.45
    AddField
    0.45
    Activations Density 0.249%

    No Known Activations