© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16278
    Prev
    Next
    INDEX
    Explanations

    expressions of internal conflict and emotional turmoil

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

    <end_of_turn> token

    np_acts-logits-general · gemini-2.0-flash

    chapter start

    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
    rungsseite
    -0.74
     ainfi
    -0.65
     للمعارف
    -0.60
     saveiro
    -0.59
     ſtand
    -0.59
     abbildung
    -0.58
     Pardavimas
    -0.57
     ſche
    -0.56
    StructEnd
    -0.56
    ientras
    -0.55
    POSITIVE LOGITS
    énario
    0.52
    Chapter
    0.40
     chapter
    0.40
     Fil
    0.36
     gro
    0.36
     Chapter
    0.36
    chapter
    0.35
    Fil
    0.34
     cad
    0.34
     دن
    0.34
    Activations Density 0.446%

    No Known Activations