© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1524
    Prev
    Next
    INDEX
    Explanations

    terms related to security and verification processes, particularly for email authentication and CSRF tokens

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

    occurrences of CAPTCHA and security-related tokens in text

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

    authentication tokens and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ztés
    -0.55
     getItemId
    -0.55
    orexia
    -0.52
     kapak
    -0.51
     conda
    -0.49
     Sang
    -0.49
    gheny
    -0.48
     segue
    -0.46
    Specifier
    -0.46
     spese
    -0.45
    POSITIVE LOGITS
     captcha
    1.15
    captcha
    1.12
    Captcha
    1.11
    CAPTCHA
    1.05
     reCAPTCHA
    0.88
     CAPT
    0.81
    验证码
    0.81
     Capt
    0.81
     кап
    0.70
     Meksiku
    0.70
    Activations Density 0.042%

    No Known Activations