Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105115
    Prev
    Next
    INDEX
    Explanations

    closing parentheses in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    ########.
    -1.02
    AsUp
    -0.89
    IndentedString
    -0.84
    UserScript
    -0.84
    transQ
    -0.82
    mpagne
    -0.82
    majánló
    -0.81
    ￳
    -0.81
     témoig
    -0.81
    ſchaft
    -0.81
    POSITIVE LOGITS
    ,
    0.38
    0
    0.37
     we
    0.34
     it
    0.34
    1
    0.31
    7
    0.31
    Exception
    0.30
     I
    0.30
     they
    0.29
    I
    0.29
    Activations Density 0.002%

    No Known Activations