© 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. 28-GEMMASCOPE-RES-16K
    11. 3769
    Prev
    Next
    INDEX
    Explanations

    words or prefixes related to "exclusion" or "exception."

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

    starting with "ex" or "Ex"

    np_acts-logits-general · gemini-2.0-flash

    words starting with ex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelves
    -0.53
     diſt
    -0.50
     ſou
    -0.49
     purpoſe
    -0.46
    ſelf
    -0.45
    Autoritní
    -0.45
     šte
    -0.43
    denly
    -0.42
     ſtate
    -0.42
    tilage
    -0.42
    POSITIVE LOGITS
     Ex
    1.18
     ex
    1.11
    ex
    1.10
    Ex
    1.03
     EX
    1.00
    EX
    0.81
     exh
    0.68
     EXC
    0.68
     eks
    0.68
    exc
    0.65
    Activations Density 0.183%

    No Known Activations