© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6992
    Prev
    Next
    INDEX
    Explanations

    keywords related to engaging with or utilizing various resources or systems

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

    tapping or harnessing

    np_acts-logits-general · gemini-2.0-flash

    tap or harness

    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
     problemet
    -0.53
    itiés
    -0.50
    ########.
    -0.50
     nothwendig
    -0.50
    nezeu
    -0.49
     betweenstory
    -0.49
     SwitchCompat
    -0.49
    bootstrapcdn
    -0.48
    Демографія
    -0.48
    省市镇
    -0.47
    POSITIVE LOGITS
     tap
    1.41
     tapped
    1.37
     Tap
    1.33
     tapping
    1.33
    Tap
    1.29
     taps
    1.26
    tap
    1.14
     TAP
    1.09
    taps
    0.98
    TAP
    0.96
    Activations Density 0.277%

    No Known Activations