© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 40995
    Prev
    Next
    INDEX
    Explanations

    references to a specific character or entity named "Cha" in various contexts

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

    Chameleon and Cha 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
     juguete
    -0.43
    <bos>
    -0.40
    autogui
    -0.38
     journaux
    -0.38
    zbęd
    -0.38
    registrer
    -0.38
     Infórmanos
    -0.38
    받
    -0.37
     προϊόν
    -0.37
    .";
    -0.36
    POSITIVE LOGITS
     Cha
    1.16
     cha
    1.07
    Cha
    1.05
     Chamb
    0.91
    cha
    0.89
     CHA
    0.88
     CHAP
    0.85
     Chak
    0.85
     chay
    0.82
     Chappell
    0.82
    Activations Density 0.016%

    No Known Activations