© 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. 2-GEMMASCOPE-RES-16K
    6. 12835
    Prev
    Next
    INDEX
    Explanations

    terms related to frames and floating-point data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    triggers
    -0.35
    Triggers
    -0.35
     ​​
    -0.34
    ​​
    -0.34
     ​
    -0.31
    ​​​​
    -0.31
     dared
    -0.31
     triggers
    -0.30
     Nie
    -0.30
     escalier
    -0.30
    POSITIVE LOGITS
    ValueStyle
    0.87
    frame
    0.77
     maths
    0.76
     math
    0.75
    math
    0.75
    mouth
    0.71
     kasarigan
    0.68
    MOUTH
    0.66
     mathematics
    0.66
    InjectAttribute
    0.66
    Activations Density 0.076%

    No Known Activations