© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1898
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges and limitations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.87
    migrationBuilder
    -0.78
    ThroughAttribute
    -0.70
    WireFormatLite
    -0.65
    ніципалі
    -0.63
     ComVisible
    -0.62
    Географиясе
    -0.61
    inguém
    -0.61
    ########.
    -0.60
     ujednoznacz
    -0.59
    POSITIVE LOGITS
     factors
    1.23
    factors
    0.93
     factores
    0.92
     reasons
    0.89
     Factors
    0.86
    Factors
    0.85
     fatores
    0.85
     Faktoren
    0.79
     facteurs
    0.78
     факторов
    0.77
    Activations Density 0.643%

    No Known Activations