© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10809
    Prev
    Next
    INDEX
    Explanations

    concepts related to change and shifting priorities in various contexts

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

    changes or shifts

    np_acts-logits-general · gemini-2.0-flash

    shifts in focus or priorities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éma
    -0.38
     rent
    -0.35
    ᅠ
    -0.31
    깥
    -0.30
    的样子
    -0.30
     bilde
    -0.29
     numerus
    -0.29
    WA
    -0.28
     Glou
    -0.28
     Gull
    -0.28
    POSITIVE LOGITS
     Changing
    0.79
     Changed
    0.78
    Changing
    0.77
     CHANG
    0.76
     changed
    0.76
     changing
    0.75
     cambiando
    0.74
     changer
    0.73
     altering
    0.73
     altered
    0.73
    Activations Density 0.859%

    No Known Activations