© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 53527
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Hall" and its variations in different contexts

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

    hall and related words

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Diego
    -0.49
     Pete
    -0.44
     Boug
    -0.43
     Diego
    -0.43
    mente
    -0.42
    Roberta
    -0.42
     Piet
    -0.40
    Pete
    -0.40
     Veronica
    -0.40
     Viet
    -0.39
    POSITIVE LOGITS
     Hall
    1.27
    Hall
    1.26
     HALL
    1.23
    hall
    1.14
     Halls
    1.11
     hall
    1.09
    HALL
    1.04
     halls
    1.03
     hallucinations
    0.84
    hallen
    0.82
    Activations Density 0.005%

    No Known Activations