© 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. 38-GEMMASCOPE-RES-16K
    11. 13400
    Prev
    Next
    INDEX
    Explanations

    specific terms related to scientific measurements and experimental protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.62
    !");
    -0.60
    ChildScrollView
    -0.59
    Were
    -0.59
    !';
    -0.59
    ."));
    -0.59
     QtWidgets
    -0.57
    __',
    -0.57
    Was
    -0.57
    "];
    -0.57
    POSITIVE LOGITS
     including
    0.47
     inclusief
    0.45
     yani
    0.45
     INCLUDING
    0.43
    つまり
    0.42
     включая
    0.42
    antaranya
    0.42
     pertaining
    0.41
     adaptarse
    0.41
     excluding
    0.41
    Activations Density 1.021%

    No Known Activations