© 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-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 13102
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols related to functions and norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Weich
    -0.33
     Speise
    -0.32
    RTLU
    -0.31
     alter
    -0.31
     hit
    -0.31
     travel
    -0.30
     flag
    -0.30
    imen
    -0.29
     Johan
    -0.29
     men
    -0.29
    POSITIVE LOGITS
    bootstrapcdn
    0.67
     nonatomic
    0.61
    esgue
    0.60
    flink
    0.57
    \|_{
    0.57
    tagHelperRunner
    0.57
    parsedMessage
    0.56
    RTSC
    0.56
    enderror
    0.54
    WriteBarrier
    0.54
    Activations Density 1.108%

    No Known Activations