Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13966
    Prev
    Next
    INDEX
    Explanations

    references to various academic or review articles and their authors

    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
     فريبيس
    -1.03
    BagLayout
    -0.91
     pygame
    -0.89
    Tikang
    -0.84
     MessageBoxIcon
    -0.81
     rospy
    -0.81
     المعيارى
    -0.80
    Bronnen
    -0.80
     OnInit
    -0.79
     lenker
    -0.76
    POSITIVE LOGITS
    *
    1.40
     *
    1.34
    //*
    1.09
     }^{*}$
    1.05
    ()*
    1.02
    :*
    1.01
     $*$
    0.97
    ?*
    0.95
    *,
    0.94
    *.
    0.94
    Activations Density 0.028%

    No Known Activations