© 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. 1-GEMMASCOPE-RES-16K
    6. 8295
    Prev
    Next
    INDEX
    Explanations

    technical or operational terms related to processes and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.82
    AsUp
    -0.80
     estekak
    -0.79
     transfieras
    -0.75
    存于互联网档案馆
    -0.74
    expandindo
    -0.74
    adaptiveStyles
    -0.74
     BoxFit
    -0.73
    OGND
    -0.72
    ագրություններ
    -0.71
    POSITIVE LOGITS
     
    0.60
    ↵↵
    0.59
     '
    0.48
     The
    0.44
     P
    0.43
     "
    0.42
     Re
    0.42
     (
    0.42
     A
    0.42
    -
    0.42
    Activations Density 4.597%

    No Known Activations