© 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. 39-GEMMASCOPE-RES-16K
    11. 4658
    Prev
    Next
    INDEX
    Explanations

    significant contrasts or unexpected findings in complex scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.44
     Мексичка
    -0.39
    ardoor
    -0.38
    EndInit
    -0.38
    そうそう
    -0.37
    GIVEREF
    -0.35
    }{*}{}
    -0.35
     meestal
    -0.34
    maksud
    -0.34
     übrigens
    -0.33
    POSITIVE LOGITS
     given
    3.08
    given
    2.70
    Given
    2.56
     Given
    2.55
     GIVEN
    2.27
     considering
    2.11
    considering
    1.95
     Considering
    1.80
    Considering
    1.80
     dado
    1.78
    Activations Density 1.523%

    No Known Activations