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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65917
    Prev
    Next
    INDEX
    Explanations

    LaTeX or mathematical expressions and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SOUNDBITE
    -0.62
    ftagPool
    -0.60
    InjectAttribute
    -0.59
    WriteTagHelper
    -0.58
     }{@
    -0.56
     يتيمه
    -0.55
     kasarigan
    -0.54
    HtmlAttribute
    -0.54
     لينك
    -0.53
    Zeneca
    -0.51
    POSITIVE LOGITS
    <eos>
    0.58
    ↵↵↵
    0.57
    ↵↵↵↵↵
    0.56
    ↵↵↵↵↵↵
    0.52
    ↵↵↵↵
    0.51
    ↵↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵
    0.46
     입니다
    0.45
    Someone
    0.44
    The
    0.42
    Activations Density 0.027%

    No Known Activations