© 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. 4698
    Prev
    Next
    INDEX
    Explanations

    expressions related to organizational transparency and accountability

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

    preceding a, ri, of, or /

    np_acts-logits-general · gemini-2.0-flash

    complex questions and paths

    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
     muß
    -0.48
    faßt
    -0.46
     guère
    -0.45
    DebuggerStep
    -0.41
    <<<<<<<<
    -0.38
     europé
    -0.37
    ]=="
    -0.36
     idéia
    -0.35
     objectForKey
    -0.34
     commonest
    -0.34
    POSITIVE LOGITS
     impactful
    0.77
     foundational
    0.72
     relatable
    0.69
     aligns
    0.69
     mentorship
    0.66
     prioriti
    0.66
     sustainability
    0.66
     resiliency
    0.65
     sustainably
    0.64
     prioritize
    0.63
    Activations Density 0.428%

    No Known Activations