© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8327
    Prev
    Next
    INDEX
    Explanations

    sentences containing strong opinions or remarks

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

    Text within quotation marks

    np_acts-logits-general · gemini-2.0-flash

    comma before quotes

    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
    MigrationBuilder
    -0.88
    Datuak
    -0.88
     فريبيس
    -0.75
    bootstrapcdn
    -0.73
    IsMutable
    -0.70
     onCreateView
    -0.70
     Signalez
    -0.69
    ########.
    -0.62
     بيها
    -0.62
     estekak
    -0.62
    POSITIVE LOGITS
     “
    0.74
     "
    0.58
     “[
    0.57
     ‘
    0.55
     «
    0.53
    jko
    0.51
     ”
    0.51
     And
    0.50
     “.
    0.49
     "}
    0.48
    Activations Density 0.115%

    No Known Activations