© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8213
    Prev
    Next
    INDEX
    Explanations

    instances of the word "implements" in the context of programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expression
    -0.57
     inc
    -0.50
    íslu
    -0.49
    `
    -0.48
    expression
    -0.46
    őd
    -0.45
    springen
    -0.44
    ive
    -0.44
     bes
    -0.43
    家主
    -0.43
    POSITIVE LOGITS
     signé
    1.09
     AssemblyCulture
    1.02
     signed
    0.99
     Signed
    0.94
    DockStyle
    0.89
     Executed
    0.89
    signed
    0.87
    Signed
    0.86
     CWE
    0.84
    esModule
    0.84
    Activations Density 0.087%

    No Known Activations