© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 111733
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and coding structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     against
    -0.33
     
    -0.32
    show
    -0.31
    Against
    -0.29
    search
    -0.29
     recon
    -0.28
     contre
    -0.28
     Q
    -0.28
     sm
    -0.28
     Mega
    -0.28
    POSITIVE LOGITS
    SharedDtor
    0.92
    verwijspagina
    0.87
    ConstraintMaker
    0.70
    ⟬
    0.67
     témoig
    0.66
    yntaxException
    0.66
     ſtate
    0.65
     disponibilités
    0.65
    WriteBarrier
    0.64
     myſelf
    0.64
    Activations Density 0.008%

    No Known Activations