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. 12-GEMMASCOPE-RES-16K
    6. 5979
    Prev
    Next
    INDEX
    Explanations

    class constructor invocations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ggior
    -0.62
     Arabian
    -0.55
    клопе
    -0.55
    ChildScrollView
    -0.54
    postsleuth
    -0.54
     Kuwa
    -0.54
     '{@
    -0.53
     betweenstory
    -0.53
     theſe
    -0.53
    ThroughAttribute
    -0.53
    POSITIVE LOGITS
     esboço
    0.65
     him
    0.62
    InlineData
    0.61
    ":"",
    0.59
    曖昧さ回避
    0.58
    ார்
    0.57
     them
    0.54
    MockBean
    0.53
    GEBURTSDATUM
    0.52
    inheritdoc
    0.52
    Activations Density 0.033%

    No Known Activations