© 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. 8-GEMMASCOPE-RES-16K
    11. 6418
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to administrative or procedural actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.51
     pleaſure
    -0.50
     purpoſe
    -0.50
     kasarigan
    -0.50
    IntoConstraints
    -0.49
    DockStyle
    -0.48
     myſelf
    -0.47
     للمعارف
    -0.47
    offsetof
    -0.46
     faſt
    -0.44
    POSITIVE LOGITS
    tered
    0.73
    cted
    0.73
    ded
    0.71
    ciated
    0.71
    ated
    0.71
    ted
    0.70
    inated
    0.70
    pted
    0.69
    ized
    0.68
    outed
    0.67
    Activations Density 1.090%

    No Known Activations