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. 20-GEMMASCOPE-RES-16K
    6. 15761
    Prev
    Next
    INDEX
    Explanations

    terms related to connectors and their connections in technical contexts

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

    preceding "and"

    np_acts-logits-general · gemini-2.0-flash

    concepts between connectors

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ,
    -0.64
    -,
    -0.61
    /
    -0.56
     but
    -0.53
     among
    -0.48
    や
    -0.47
    ・
    -0.45
    ?,?,
    -0.43
    なども
    -0.43
    やお
    -0.43
    POSITIVE LOGITS
    তথ্যসূত্র
    0.89
    findpost
    0.84
     กับ
    0.81
     CURIAM
    0.81
    Kaynakça
    0.80
     cref
    0.79
    tvguidetime
    0.78
    NUMX
    0.78
    ChildScrollView
    0.76
     einerseits
    0.74
    Activations Density 0.715%

    No Known Activations