© 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. 2125
    Prev
    Next
    INDEX
    Explanations

    terms related to research studies and their methodologies

    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
    IntoConstraints
    -0.92
    stdc
    -0.68
     مرئيه
    -0.60
    forChild
    -0.58
    RectangleBorder
    -0.57
     насељу
    -0.55
    BASEPATH
    -0.55
    jestel
    -0.52
     дописавши
    -0.52
     >=",
    -0.50
    POSITIVE LOGITS
     autorytatywna
    0.68
     CreateTagHelper
    0.56
    haku
    0.56
    Jeografia
    0.55
    })$}
    0.54
    lably
    0.53
    eabouts
    0.53
    rawDesc
    0.52
     primarily
    0.51
    ueuse
    0.51
    Activations Density 0.764%

    No Known Activations