© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 6235
    Prev
    Next
    INDEX
    Explanations

    references to SSH protocols and associated commands, particularly focusing on security keys and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     A
    -0.68
    A
    -0.59
     S
    -0.52
     D
    -0.47
     C
    -0.45
     B
    -0.45
     T
    -0.43
     R
    -0.43
    B
    -0.42
    C
    -0.40
    POSITIVE LOGITS
    AndEndTag
    0.91
    parsedMessage
    0.87
     ſind
    0.87
    Autoritní
    0.85
     queſta
    0.84
     виправивши
    0.81
     AssemblyCompany
    0.81
    ConstraintMaker
    0.79
    featureID
    0.79
     مشين
    0.79
    Activations Density 1.688%

    No Known Activations