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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5160
    Prev
    Next
    INDEX
    Explanations

    programming logic and control structures in code.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code snippets related to programming.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    input/output operations in programming or electronic contexts.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Code involving "input" and "output"

    np_acts-logits-general · gemini-2.0-flash

    input and output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    
    -0.68
    AndEndTag
    -0.66
    createServer
    -0.57
     vPvB
    -0.54
    WriteBarrier
    -0.53
     SDC
    -0.52
    찮
    -0.52
    IonicModule
    -0.51
    +:+
    -0.51
     виправивши
    -0.51
    POSITIVE LOGITS
     input
    2.60
    input
    2.36
     Input
    2.34
    Input
    2.22
     INPUT
    2.17
     inputs
    2.12
    INPUT
    2.11
     output
    1.94
    getInput
    1.85
     Inputs
    1.84
    Activations Density 0.116%

    No Known Activations