© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12701
    Prev
    Next
    INDEX
    Explanations

    positive adjectives that describe qualities or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.74
    yntaxException
    -0.66
    HtmlAttribute
    -0.64
    KEYCODE
    -0.61
     SearchView
    -0.58
    SequentialGroup
    -0.58
    bootstrapcdn
    -0.57
    UnifiedTopology
    -0.56
    meteries
    -0.56
    DateField
    -0.56
    POSITIVE LOGITS
     wonderful
    1.32
     marvelous
    1.25
     amazing
    1.25
    amazing
    1.20
    wonderful
    1.18
     fantastic
    1.18
     excellent
    1.17
     terrific
    1.15
    fantastic
    1.14
     splendid
    1.13
    Activations Density 0.146%

    No Known Activations