© 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. 5364
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements and documentation references

    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
    Похо
    -0.52
    elemField
    -0.52
    meck
    -0.48
     AllAfrica
    -0.48
    /#/
    -0.47
    Palindrome
    -0.45
    rag
    -0.45
     CCD
    -0.43
    ness
    -0.41
    iero
    -0.41
    POSITIVE LOGITS
     оригіналу
    0.91
    ">//
    0.87
    }")]
    0.84
     purpoſe
    0.83
    TagMode
    0.81
    帖最后由
    0.80
    ISupport
    0.80
     الاطلاع
    0.75
    Geplaatst
    0.74
    AutoScale
    0.74
    Activations Density 0.005%

    No Known Activations