© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13264
    Prev
    Next
    INDEX
    Explanations

    placeholders and prompts within input forms

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

    "Placeholder" or similar text

    np_acts-logits-general · gemini-2.0-flash

    placeholder and hint text for inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngrx
    -0.87
    ValueStyle
    -0.82
     Signalez
    -0.75
    ロウィン
    -0.74
    migrationBuilder
    -0.73
    providedIn
    -0.73
     Administrativna
    -0.71
    BagConstraints
    -0.69
     CreateTagHelper
    -0.69
    httphttps
    -0.68
    POSITIVE LOGITS
     placeholder
    0.73
    placeholder
    0.72
    Placeholder
    0.60
    hintText
    0.59
    PlaceHolder
    0.50
     Placeholder
    0.42
    HINT
    0.38
    hint
    0.35
     anzunehmen
    0.31
    label
    0.30
    Activations Density 0.018%

    No Known Activations