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. 16-GEMMASCOPE-RES-16K
    6. 14986
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and genetic research, particularly in the context of mental health and disorders

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

    studies and researchers

    np_acts-logits-general · gemini-2.0-flash

    researchers reporting findings

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    GraphicsUnit
    -0.90
    RectangleBorder
    -0.85
    TypedDataSet
    -0.85
    IndentedString
    -0.80
    MLLoader
    -0.78
     Efq
    -0.77
     utafitiHapana
    -0.77
    ChildScrollView
    -0.76
     myſelf
    -0.75
    EDEFAULT
    -0.74
    POSITIVE LOGITS
     researchers
    1.04
    Researchers
    0.87
     study
    0.80
     Researchers
    0.76
     investigadores
    0.74
     scientists
    0.72
     chercheurs
    0.70
     researcher
    0.67
     findings
    0.66
     investigators
    0.62
    Activations Density 0.362%

    No Known Activations