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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 4264
    Prev
    Next
    INDEX
    Explanations

    concepts related to physical and mental well-being, particularly those that address the health of youth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.64
     dared
    -0.54
    GraphicsUnit
    -0.52
    ห์
    -0.51
     ModelExpression
    -0.50
    stdafx
    -0.49
    =====
    -0.46
     doubted
    -0.45
     مرئيه
    -0.45
     BoxDecoration
    -0.44
    POSITIVE LOGITS
     healthy
    0.73
     stabilité
    0.68
     stability
    0.65
    healthy
    0.64
    Healthy
    0.62
     healthful
    0.61
     Healthy
    0.59
    perity
    0.58
     healthier
    0.58
     stable
    0.57
    Activations Density 0.254%

    No Known Activations