© 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. 31-GEMMASCOPE-RES-16K
    11. 1153
    Prev
    Next
    INDEX
    Explanations

    terms related to inclusivity and comprehensiveness in various contexts

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

    superlative or emphatic descriptions using the structure "as [adjective] a [noun]".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.54
    ttemberg
    -0.51
     kasarigan
    -0.49
    utilisons
    -0.48
     EconPapers
    -0.48
    mybatisplus
    -0.45
    DECREF
    -0.45
    Hentet
    -0.45
    出版年
    -0.43
    :✨
    -0.42
    POSITIVE LOGITS
     a
    0.85
     an
    0.58
    a
    0.40
    readonly
    0.37
    remaining
    0.36
    いいのか
    0.36
     restantes
    0.36
     defaultstate
    0.35
     restante
    0.33
    astic
    0.33
    Activations Density 0.203%

    No Known Activations