© 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. 10148
    Prev
    Next
    INDEX
    Explanations

    references to stone and related materials

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

    "stone" or its pluralization

    np_acts-logits-general · gemini-2.0-flash

    stone and related objects

    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
     lenker
    -0.58
     onOptions
    -0.51
    XmlAccessType
    -0.48
     asyncio
    -0.46
     ब्रेकडाउन
    -0.44
    thical
    -0.43
    AndEndTag
    -0.43
    phorus
    -0.43
    DockStyle
    -0.43
    Rujuakan
    -0.43
    POSITIVE LOGITS
     stone
    2.31
     Stone
    2.06
    Stone
    2.02
     STONE
    1.98
     stones
    1.89
    stone
    1.83
    STONE
    1.70
     Stones
    1.63
    stones
    1.59
    Stones
    1.58
    Activations Density 0.184%

    No Known Activations