© 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. 20-GEMMASCOPE-RES-16K
    11. 13883
    Prev
    Next
    INDEX
    Explanations

    words related to destruction and defeat

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

    "[something] destroyed by"

    np_acts-logits-general · gemini-2.0-flash

    destroyed by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.55
     المعيارى
    -0.52
    ReusableCell
    -0.50
     '\\;'
    -0.50
    SPATH
    -0.47
    Jeografia
    -0.46
     estekak
    -0.44
     للمعارف
    -0.44
     wireType
    -0.43
    Fordítás
    -0.43
    POSITIVE LOGITS
     destroyed
    0.49
    rmtree
    0.47
     destroying
    0.45
     destroys
    0.45
     destruction
    0.44
    onDestroy
    0.41
     Destroy
    0.40
     onResponse
    0.40
     onDestroy
    0.39
    Destroyed
    0.39
    Activations Density 0.596%

    No Known Activations