© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1980
    Prev
    Next
    INDEX
    Explanations

    relationships between concepts and consequences

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

    ending in "ic", "ss", "th", "rt", "my", or "er"

    np_acts-logits-general · gemini-2.0-flash

    general concepts and domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enablog
    -0.75
    ⟬
    -0.73
    RenderAtEndOf
    -0.66
     lenker
    -0.66
     tartalo
    -0.66
     ſoll
    -0.65
    ₶
    -0.65
    ſicht
    -0.64
     geweſen
    -0.64
    [@BOS@]
    -0.64
    POSITIVE LOGITS
     regardless
    0.34
     whether
    0.34
     so
    0.34
     sometimes
    0.33
     nowadays
    0.31
     unless
    0.30
     होता
    0.30
     often
    0.30
     any
    0.30
     होती
    0.29
    Activations Density 0.693%

    No Known Activations