© 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. 13519
    Prev
    Next
    INDEX
    Explanations

    steps or instructions in a procedural context

    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
     BrowserModule
    -0.48
     venit
    -0.46
    uvwxyz
    -0.45
     Taktlose
    -0.43
     paš
    -0.43
     homelessness
    -0.43
    (@"%@",
    -0.42
     faltan
    -0.42
    dshaw
    -0.42
    äsentation
    -0.42
    POSITIVE LOGITS
    step
    0.69
    Step
    0.62
     pet
    0.61
     step
    0.52
    CrossRef
    0.52
     usize
    0.51
    CloseOperation
    0.48
     Step
    0.47
    enumi
    0.43
    findById
    0.43
    Activations Density 0.126%

    No Known Activations