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. 9-GEMMASCOPE-RES-16K
    6. 1512
    Prev
    Next
    INDEX
    Explanations

    structural elements of documents, particularly sections and formatting codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    āciju
    -0.59
    ACCIÓN
    -0.57
    ázquez
    -0.57
    dings
    -0.56
     Judith
    -0.56
     domy
    -0.56
     Cryst
    -0.55
     Nawaz
    -0.55
     Chuan
    -0.54
     Theſe
    -0.54
    POSITIVE LOGITS
     gyhoeddwyd
    0.79
    WriteBarrier
    0.65
    下载附件
    0.63
     Biôgrafia
    0.60
     Drapeau
    0.60
     تكبرها
    0.60
    Попис
    0.58
    IUrlHelper
    0.58
     resourceCulture
    0.56
     مشين
    0.54
    Activations Density 0.130%

    No Known Activations