© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1275
    Prev
    Next
    INDEX
    Explanations

    terminology related to electrical circuits and operational amplifiers

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

    relationships between inputs and outputs in a graph or circuit context

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

    output and input connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Демографія
    -0.66
     cellspacing
    -0.54
     CRL
    -0.52
    AndEndTag
    -0.51
     myeloma
    -0.51
     vPvB
    -0.51
     Normdatei
    -0.50
    ثيق
    -0.49
    arabe
    -0.49
    MessageOf
    -0.48
    POSITIVE LOGITS
     output
    1.25
     outputs
    1.21
    output
    1.18
     Output
    1.18
    Output
    1.10
     Outputs
    1.07
    输出
    1.03
    OUTPUT
    1.02
     OUTPUT
    1.01
     inputs
    1.00
    Activations Density 0.214%

    No Known Activations