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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5728
    Prev
    Next
    INDEX
    Explanations

    references to serializable classes and related code structures

    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
    useEffect
    -1.13
     useEffect
    -0.86
     kvar
    -0.55
     fun
    -0.51
    hette
    -0.49
    ableness
    -0.49
     tr
    -0.49
    esign
    -0.48
    Distribución
    -0.47
     따
    -0.47
    POSITIVE LOGITS
     OnInit
    5.39
    OnInit
    1.67
    ViewInit
    1.37
    
    1.11
    MemoryWarning
    1.07
     OnDestroy
    1.06
    providedIn
    1.04
     HasFactory
    1.04
    webElementXpaths
    1.03
    ngOnInit
    0.95
    Activations Density 0.017%

    No Known Activations