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. 16-GEMMASCOPE-RES-16K
    6. 5104
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and structures related to document preparation and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or code-like text

    np_acts-logits-general · gemini-2.0-flash

    certain type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.74
     Rptr
    -0.63
    Tazama
    -0.63
    NegativeButton
    -0.61
    {{/
    -0.57
    Rptr
    -0.56
    HtmlAttribute
    -0.55
     NUKAT
    -0.54
     jefes
    -0.54
    NgModule
    -0.54
    POSITIVE LOGITS
    leby
    0.56
     betweenstory
    0.54
    cuba
    0.48
     kasarigan
    0.46
    NotEqualTo
    0.45
     Gruß
    0.45
    reportWebVitals
    0.45
    ↵↵↵↵
    0.45
    })();
    
    0.45
    évaluateur
    0.45
    Activations Density 0.050%

    No Known Activations