© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 11018
    Prev
    Next
    INDEX
    Explanations

    code constructs related to input and output operations/functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.55
    createServer
    -0.52
    AndEndTag
    -0.49
    locke
    -0.48
    навли
    -0.48
    epam
    -0.47
    ALSE
    -0.47
    찮
    -0.47
     SDC
    -0.46
     Waray
    -0.46
    POSITIVE LOGITS
     input
    2.76
     Input
    2.55
    input
    2.53
    Input
    2.41
     inputs
    2.31
     INPUT
    2.30
    INPUT
    2.21
     output
    2.07
     Inputs
    2.02
    输入
    1.94
    Activations Density 0.110%

    No Known Activations