© 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. 24-GEMMASCOPE-RES-16K
    11. 5886
    Prev
    Next
    INDEX
    Explanations

    specific references to legal cases and the impact of environmental factors

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

    Appears before special characters

    np_acts-logits-general · gemini-2.0-flash

    legal / medical / technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Albrecht
    -0.53
    ★☆
    -0.52
     virt
    -0.51
    ​—
    -0.50
     Sö
    -0.48
     Hawkins
    -0.48
     kasarigan
    -0.47
    lerc
    -0.47
     Stephens
    -0.47
    isamment
    -0.47
    POSITIVE LOGITS
     Gewähr
    0.48
    jsx
    0.45
     Doe
    0.44
     veau
    0.43
     dough
    0.43
     senderismo
    0.42
    neurial
    0.42
     tesettür
    0.42
     Sahel
    0.41
    resume
    0.41
    Activations Density 1.279%

    No Known Activations