© 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
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8575
    Prev
    Next
    INDEX
    Explanations

    references to secrecy and hidden information related to security matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.54
    ardige
    -0.53
    astify
    -0.53
    AutoField
    -0.52
    wapV
    -0.48
    outSlope
    -0.46
    culada
    -0.46
    Rptr
    -0.45
    AndEndTag
    -0.45
     @"/
    -0.44
    POSITIVE LOGITS
     secret
    0.66
     secrecy
    0.65
     secrets
    0.64
     confidential
    0.64
     hidden
    0.62
    Confidential
    0.60
     geheim
    0.59
     confidentiality
    0.57
     concealed
    0.57
     privacy
    0.57
    Activations Density 0.373%

    No Known Activations