© 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. 9-GEMMASCOPE-RES-16K
    6. 9578
    Prev
    Next
    INDEX
    Explanations

    numerical values related to data sets and measurements

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

    numeric identifiers or product/model numbers, particularly those with digit sequences.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.84
    principalTable
    -0.69
     nakalista
    -0.68
    ParallelGroup
    -0.65
    PerformLayout
    -0.65
     wireType
    -0.65
     Мексичка
    -0.62
    setVerticalGroup
    -0.61
     Italijani
    -0.61
     ***!
    -0.59
    POSITIVE LOGITS
     Vernunft
    0.53
     democrá
    0.46
     matrícula
    0.40
     democrática
    0.40
     fotográfica
    0.40
     wobec
    0.39
    AGON
    0.39
     honneur
    0.39
     associée
    0.38
    淼
    0.37
    Activations Density 1.488%

    No Known Activations