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. 1-GEMMASCOPE-RES-16K
    6. 5940
    Prev
    Next
    INDEX
    Explanations

    terms related to bone and skeletal anatomy or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lær
    -0.51
    essex
    -0.50
    uero
    -0.48
    Baca
    -0.47
    zyści
    -0.47
     conversión
    -0.47
    apprentissage
    -0.46
     fermés
    -0.45
    bangun
    -0.45
     aprendizaje
    -0.45
    POSITIVE LOGITS
    ConstraintMaker
    0.81
     bone
    0.78
    bone
    0.74
     Bone
    0.74
     bones
    0.74
    Bone
    0.71
    bones
    0.68
    Anonymous
    0.68
     Anonymous
    0.66
    adpleegd
    0.65
    Activations Density 2.385%

    No Known Activations