© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1797
    Prev
    Next
    INDEX
    Explanations

    expressions and phrases indicating oddity or strangeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     referenties
    -0.77
    شرين
    -0.67
     بتاريخ
    -0.67
    timbangkan
    -0.67
    IsContent
    -0.66
     ComVisible
    -0.66
     coals
    -0.66
     stomat
    -0.64
    createCanvas
    -0.64
    ciutto
    -0.62
    POSITIVE LOGITS
     strange
    1.26
     Strange
    1.25
    strange
    1.17
     Weird
    1.16
     weird
    1.16
    Strange
    1.12
     bizarre
    1.12
    weird
    1.11
     wierd
    1.10
     étrange
    1.09
    Activations Density 0.125%

    No Known Activations