Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10928
    Prev
    Next
    INDEX
    Explanations

    references and terms related to polymers, particularly poly(mers) and their variants

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

    The prefix "poly" attached to various words

    np_acts-logits-general · gemini-2.0-flash

    words starting with poly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.65
    httphttps
    -0.63
    GEBURTSDATUM
    -0.62
    tagext
    -0.58
    Ārējās
    -0.52
     kasarigan
    -0.50
     absorción
    -0.50
    WireFormatLite
    -0.49
     Erwä
    -0.49
    Personensuche
    -0.48
    POSITIVE LOGITS
     Poly
    0.99
     poly
    0.98
     POLY
    0.84
    Poly
    0.81
    poly
    0.74
     polyg
    0.68
    POLY
    0.68
     Polytechnic
    0.57
     poli
    0.56
     Polly
    0.53
    Activations Density 0.152%

    No Known Activations