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. 20-GEMMASCOPE-RES-65K
    6. 448
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or statements

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

    conditional phrases related to instructions or requirements

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

    if any

    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
     كومونز
    -0.60
    bnf
    -0.55
    帖最后由
    -0.52
    逆に
    -0.48
     cependant
    -0.45
    mockito
    -0.45
    AddHtmlAttribute
    -0.45
     pleno
    -0.44
    但是在
    -0.44
     viens
    -0.43
    POSITIVE LOGITS
     applicable
    1.67
    applicable
    1.41
     Applicable
    1.20
     appropriate
    1.13
     relevant
    1.05
     APPLICABLE
    1.02
     aplicable
    1.00
    Applicable
    0.97
    appropriate
    0.84
    Appropriate
    0.83
    Activations Density 0.086%

    No Known Activations