© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12047
    Prev
    Next
    INDEX
    Explanations

    phrases that promote actions or behaviors

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

    "You" followed by advice/suggestions

    np_acts-logits-general · gemini-2.0-flash

    you should consider

    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
    -0.62
    providedIn
    -0.57
     okuyayım
    -0.55
     snippetHide
    -0.54
     estrena
    -0.54
     Scritto
    -0.52
    
    -0.50
    OGND
    -0.50
     brilliance
    -0.49
    개
    -0.49
    POSITIVE LOGITS
     consider
    1.07
     beware
    0.84
     reconsider
    0.81
     Consider
    0.79
     check
    0.78
    #+#
    0.77
    consider
    0.74
     think
    0.72
     considering
    0.71
     remember
    0.71
    Activations Density 0.244%

    No Known Activations