© 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. 11-GEMMASCOPE-RES-16K
    11. 6613
    Prev
    Next
    INDEX
    Explanations

    code related to GPU and device management functions in the CUDA programming environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.89
    ValueStyle
    -0.64
    awtextra
    -0.63
    těte
    -0.61
     CreateTagHelper
    -0.60
    CompilerServices
    -0.60
    featureID
    -0.60
    abestanden
    -0.59
     nakalista
    -0.58
     يتيمه
    -0.57
    POSITIVE LOGITS
     sockaddr
    0.48
     življen
    0.42
     nemico
    0.42
    сій
    0.42
    RenderAtEndOf
    0.42
     PERSON
    0.41
    ález
    0.40
    Rhestr
    0.40
    GraphicsUnit
    0.40
    ChildScrollView
    0.40
    Activations Density 0.592%

    No Known Activations