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. 12-GEMMASCOPE-RES-16K
    6. 14420
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting indicators

    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
    IntoConstraints
    -0.93
     فريبيس
    -0.91
    tableFuture
    -0.90
    richTextPanel
    -0.90
     Roskov
    -0.84
    RetentionPolicy
    -0.83
     cdti
    -0.83
    ChildScrollView
    -0.82
    KommentareTeilen
    -0.80
     Audiodateien
    -0.79
    POSITIVE LOGITS
    たまた
    0.50
    ps
    0.50
    ans
    0.48
     дописавши
    0.47
     ред
    0.46
    ats
    0.46
    Skipped
    0.44
     CommonModule
    0.42
    HtmlAttribute
    0.42
    By
    0.42
    Activations Density 0.505%

    No Known Activations