© 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. 20-GEMMASCOPE-RES-16K
    6. 2036
    Prev
    Next
    INDEX
    Explanations

    terms related to data processing and management in computing systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical descriptions of distributed computing systems, particularly focusing on software architecture, data processing, and system management.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.66
    VersionUID
    -0.42
    脚注の使い方
    -0.41
    ギュ
    -0.40
     scented
    -0.38
    rxjs
    -0.38
     Mrs
    -0.38
    intios
    -0.37
     February
    -0.37
     bitterly
    -0.37
    POSITIVE LOGITS
     BorderSide
    0.46
     integral
    0.46
     interfaces
    0.45
     interface
    0.45
     communication
    0.44
     klienta
    0.42
     middleware
    0.42
     external
    0.42
     processing
    0.41
     intermediate
    0.41
    Activations Density 0.760%

    No Known Activations