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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14184
    Prev
    Next
    INDEX
    Explanations

    legal terms and formal copyright references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.39
     stand
    -0.35
     computer
    -0.34
     ball
    -0.33
     Ball
    -0.32
    ↵↵
    -0.32
     type
    -0.31
    -
    -0.31
     trial
    -0.31
     cash
    -0.31
    POSITIVE LOGITS
    AddTagHelper
    9.75
    AddHtmlAttribute
    1.90
     CreateTagHelper
    1.85
    WriteTagHelper
    1.64
    RenderAtEndOf
    1.55
    WriteAttribute
    1.37
    ValueStyle
    1.35
    enterOuterAlt
    1.28
    setVerticalGroup
    1.23
    GOTREF
    1.18
    Activations Density 0.007%

    No Known Activations