© 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. 15-GEMMASCOPE-RES-16K
    11. 4897
    Prev
    Next
    INDEX
    Explanations

    references to appeals or legal terminologies related to hearings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.62
    terday
    -0.61
     DENSITY
    -0.59
     éto
    -0.58
    endaft
    -0.56
    estacks
    -0.55
    دانشنامهٔ
    -0.55
     cuchar
    -0.55
    filesize
    -0.55
    tagHelperRunner
    -0.55
    POSITIVE LOGITS
     Re
    0.82
    Re
    0.77
     Pro
    0.66
     Co
    0.64
    Pro
    0.62
     pro
    0.59
     De
    0.57
     pre
    0.57
     sp
    0.57
     dis
    0.56
    Activations Density 0.487%

    No Known Activations