Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1106
    Prev
    Next
    INDEX
    Explanations

    terms related to security and policing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.55
    ondheim
    -0.53
    esModule
    -0.51
     hå
    -0.50
     laborales
    -0.47
    MLLoader
    -0.46
    fjspx
    -0.46
    ⓧ
    -0.46
     ChromeDriver
    -0.46
     HttpStatusCode
    -0.45
    POSITIVE LOGITS
     security
    1.73
     Security
    1.50
    Security
    1.43
    security
    1.43
     SECURITY
    1.27
     Sicherheits
    1.27
    SECURITY
    1.23
     safety
    1.21
     police
    1.17
     policing
    1.10
    Activations Density 0.283%

    No Known Activations