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. 10-GEMMASCOPE-RES-16K
    6. 11649
    Prev
    Next
    INDEX
    Explanations

    file path references and directory structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.57
    GOTREF
    -0.54
     either
    -0.49
     opérés
    -0.49
    twimg
    -0.48
    帖最后由
    -0.47
    ظام
    -0.47
     mess
    -0.44
     whose
    -0.44
    tev
    -0.43
    POSITIVE LOGITS
    SourceChecksum
    0.75
    دانشنامهٔ
    0.68
    出版年
    0.65
     betweenstory
    0.62
    tagHelperRunner
    0.59
    ScopeManager
    0.54
     Maggiore
    0.53
     Seneca
    0.52
    UnitTesting
    0.51
     superstitions
    0.51
    Activations Density 0.177%

    No Known Activations