Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2975
    Prev
    Next
    INDEX
    Explanations

    elements and notation related to mathematical sets and projections

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

    Mathematical or logical rightwards arrows

    np_acts-logits-general · gemini-2.0-flash

    arrows and mappings

    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
    matchCondition
    -0.75
     ferons
    -0.58
     архивлан
    -0.58
    jude
    -0.57
     nakalista
    -0.56
     ujednoznacz
    -0.56
    webElementGuid
    -0.56
    richTextPanel
    -0.54
    ništ
    -0.53
    WEBPACK
    -0.52
    POSITIVE LOGITS
     →
    1.50
     ->
    1.42
    →
    1.37
    ->
    1.28
     -->
    1.20
    -->
    1.10
    rightarrow
    1.06
     =>
    1.00
    ]->
    0.99
     --->
    0.97
    Activations Density 0.731%

    No Known Activations