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. 5026
    Prev
    Next
    INDEX
    Explanations

    mention of authority and legal claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     виправивши
    -0.58
    astify
    -0.58
    HostException
    -0.53
     JpaRepository
    -0.53
     leçon
    -0.53
    Disliked
    -0.53
    HomeAsUpEnabled
    -0.52
    नीय
    -0.50
     appreciation
    -0.47
    ForRow
    -0.47
    POSITIVE LOGITS
     claim
    2.56
     claimed
    2.54
     claims
    2.53
     claiming
    2.42
     Claims
    2.23
    claim
    2.16
     Claim
    2.15
     CLAIM
    2.14
    claims
    2.12
     CLAIMS
    2.08
    Activations Density 0.480%

    No Known Activations