© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 15887
    Prev
    Next
    INDEX
    Explanations

    nouns and pronouns related to subjects and their actions within contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ssaint
    -0.45
     Miller
    -0.44
     if
    -0.43
     Im
    -0.43
    pretation
    -0.43
    Referanser
    -0.42
     and
    -0.42
    fikasi
    -0.41
     know
    -0.41
    ylus
    -0.40
    POSITIVE LOGITS
     Simba
    0.78
     Heisenberg
    0.78
    ineno
    0.76
    <>());
    0.75
     SIAM
    0.74
     allAfrica
    0.72
     heme
    0.71
     Deity
    0.71
     BitmapFactory
    0.70
    BASEPATH
    0.70
    Activations Density 0.655%

    No Known Activations