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. 13-GEMMASCOPE-RES-16K
    6. 8389
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "roll" and its derivatives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abrigo
    -0.47
     keselamatan
    -0.47
     ligiloj
    -0.47
    */].
    -0.46
     veiligheid
    -0.46
     repuesto
    -0.46
     esforço
    -0.45
     väh
    -0.45
     perigo
    -0.44
     jueces
    -0.43
    POSITIVE LOGITS
     roll
    1.65
     ROLL
    1.56
     rolling
    1.56
     Roll
    1.55
     rolls
    1.52
     Rolling
    1.51
     rolled
    1.49
    Roll
    1.48
    roll
    1.47
    Rolling
    1.41
    Activations Density 0.178%

    No Known Activations