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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 8999
    Prev
    Next
    INDEX
    Explanations

    references to statistical methods and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </caption>
    -0.62
    hoeddwyd
    -0.56
    verwijspagina
    -0.54
    äiv
    -0.54
     فريبيس
    -0.53
     BoxFit
    -0.53
    matchCondition
    -0.52
     &___
    -0.51
    सन्दर्भ
    -0.50
    hematics
    -0.48
    POSITIVE LOGITS
    IBOutlet
    0.59
    aarrggbb
    0.57
     متعلقه
    0.54
    Click
    0.53
     magique
    0.52
     africain
    0.52
    Manbalar
    0.49
     espagne
    0.49
     grecque
    0.49
     ContentValues
    0.48
    Activations Density 0.201%

    No Known Activations