© 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. 33-GEMMASCOPE-RES-16K
    11. 8187
    Prev
    Next
    INDEX
    Explanations

    references to questions, choices, and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StandardCharsets
    -0.34
    StoryboardSegue
    -0.34
     ss
    -0.33
     ap
    -0.33
     Oss
    -0.33
     hy
    -0.31
     Os
    -0.29
    intios
    -0.29
    ={<
    -0.28
     characteristic
    -0.28
    POSITIVE LOGITS
    ScopeManager
    0.77
     siitä
    0.71
    ว่า
    0.64
    awtextra
    0.59
    новништво
    0.58
     HOW
    0.54
    至于
    0.54
     cómo
    0.54
    如何在
    0.54
     איך
    0.53
    Activations Density 0.344%

    No Known Activations