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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53427
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to hip dislocation and associated conditions or factors

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

    slight change or move

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spill
    -0.53
    SBATCH
    -0.51
    SerializedName
    -0.48
    NamedQueries
    -0.46
    POSURE
    -0.46
     spills
    -0.45
     ISNI
    -0.45
     reput
    -0.44
     mengen
    -0.44
    StatusOK
    -0.43
    POSITIVE LOGITS
    ImageContext
    0.70
    исленность
    0.67
     élas
    0.63
     Vikipedi
    0.62
    Jeografia
    0.61
    Демографія
    0.60
     >=",
    0.60
    Personendaten
    0.60
    évaluateur
    0.60
    ArrowToggle
    0.60
    Activations Density 0.180%

    No Known Activations