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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2701
    Prev
    Next
    INDEX
    Explanations

    patterns of code related to regular expressions and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 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
    ['
    -0.38
    s
    -0.34
     [`
    -0.34
    GOTREF
    -0.33
    ApiModel
    -0.33
    IBOutlet
    -0.31
    छे
    -0.31
     hasard
    -0.31
    SOUNDBITE
    -0.31
    UserScript
    -0.31
    POSITIVE LOGITS
    :[
    0.92
    ).[
    0.77
     plufieurs
    0.76
    .[
    0.73
    ',[
    0.71
    ![
    0.71
    },[
    0.69
    ?[
    0.67
     feroit
    0.67
    ={[
    0.65
    Activations Density 0.630%

    No Known Activations