© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 28280
    Prev
    Next
    INDEX
    Explanations

    medical conditions related to eye health

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

    typically accounts for or predominates

    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
    הערות
    -0.73
     विश्वसनीयता
    -0.60
    Демографія
    -0.57
    \{\\
    -0.57
    romyal
    -0.56
    MessageTagHelper
    -0.55
     schlagen
    -0.53
     transfieras
    -0.52
    UNIQUE
    -0.52
    __':
    -0.51
    POSITIVE LOGITS
     predominate
    0.67
     predomin
    0.67
     typically
    0.66
     predominant
    0.66
     usually
    0.65
    Typically
    0.65
     typ
    0.64
     defaultstate
    0.62
     generally
    0.58
     mostly
    0.58
    Activations Density 0.260%

    No Known Activations