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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15507
    Prev
    Next
    INDEX
    Explanations

    references to softness and related qualities in various contexts

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

    "soft" and related terms

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
     idéia
    -0.42
     lentejuelas
    -0.40
     campeones
    -0.38
     cremallera
    -0.38
     huellas
    -0.36
     agujeros
    -0.36
     volando
    -0.35
     galaxia
    -0.35
     masiva
    -0.35
    kwür
    -0.35
    POSITIVE LOGITS
     Soft
    1.31
     soft
    1.28
    Soft
    1.20
     SOFT
    1.16
    soft
    1.16
    SOFT
    1.11
     softness
    1.03
     softer
    0.95
     Sof
    0.89
    软
    0.86
    Activations Density 0.076%

    No Known Activations