© 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. 9-GEMMASCOPE-RES-131K
    11. 6724
    Prev
    Next
    INDEX
    Explanations

    mentions of security protocols and encryption mechanisms

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

    SSL, TLS, HTTPS, VPN, certificates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Commune
    -0.50
     FAP
    -0.49
     Fah
    -0.49
    Hara
    -0.48
    ITECH
    -0.46
    imothy
    -0.43
    Hare
    -0.43
    RectangleBorder
    -0.43
     favourite
    -0.41
     Carpenter
    -0.41
    POSITIVE LOGITS
    SSL
    2.42
     SSL
    2.38
     ssl
    1.79
    ssl
    1.71
    Ssl
    1.42
     OpenSSL
    0.91
     TLS
    0.89
    TLS
    0.84
     tls
    0.79
     HTTPS
    0.77
    Activations Density 0.003%

    No Known Activations