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. 11-GEMMASCOPE-RES-16K
    6. 5150
    Prev
    Next
    INDEX
    Explanations

    references to floating-point data types and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kinds
    -0.46
    hner
    -0.45
     moeite
    -0.42
    done
    -0.40
     Cory
    -0.40
     kindred
    -0.40
    kinds
    -0.40
     done
    -0.39
    rew
    -0.39
    SharedDtor
    -0.38
    POSITIVE LOGITS
     float
    2.00
     Float
    1.95
    float
    1.82
     FLOAT
    1.80
    Float
    1.79
     floats
    1.71
     floated
    1.48
    FLOAT
    1.48
     floating
    1.45
     Floating
    1.43
    Activations Density 0.114%

    No Known Activations