© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4115
    Prev
    Next
    INDEX
    Explanations

    references to chains 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 @ 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
     jsPsych
    -0.48
    帖最后由
    -0.47
     autorytatywna
    -0.46
     propOrder
    -0.45
     sanoo
    -0.45
    клопе
    -0.45
     AssemblyTitle
    -0.44
    willReturn
    -0.43
    omitempty
    -0.43
     Kammer
    -0.43
    POSITIVE LOGITS
     chain
    1.46
     Chain
    1.19
    chain
    1.17
     chains
    1.15
     CHAIN
    1.08
    Chain
    1.04
    CHAIN
    0.93
    chains
    0.91
     Chains
    0.91
     catena
    0.91
    Activations Density 0.072%

    No Known Activations