© 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. 38-GEMMASCOPE-RES-16K
    11. 7540
    Prev
    Next
    INDEX
    Explanations

    connections and relationships, particularly those involving negation or duality in contexts such as government, lineage, and circumstances

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

    structures using "neither...nor" to negate two contrasting alternatives.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WITHOUT
    -0.45
     WITHOUT
    -0.44
    دانشنامهٔ
    -0.43
    Rüyada
    -0.42
    ()==
    -0.40
    expandindo
    -0.40
     Без
    -0.38
    但不
    -0.37
    )==
    -0.37
     without
    -0.37
    POSITIVE LOGITS
     nor
    4.00
    nor
    3.02
     Nor
    2.91
    Nor
    2.84
     NOR
    2.23
     Tampoco
    2.13
     tampoco
    2.09
     neither
    2.08
    NOR
    2.03
    neither
    1.83
    Activations Density 1.332%

    No Known Activations