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. 65941
    Prev
    Next
    INDEX
    Explanations

    specific data structure elements, particularly those related to names and reference attributes

    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
     AspNetCore
    -0.42
     يتيمه
    -0.34
    setArguments
    -0.31
    BorderSize
    -0.30
    idão
    -0.29
     sc
    -0.28
     Parliament
    -0.28
    납
    -0.27
     Parlament
    -0.26
    $}}
    -0.26
    POSITIVE LOGITS
     ProtoMessage
    0.65
    évaluateur
    0.64
     kasarigan
    0.60
     resourceCulture
    0.57
     AssemblyCompany
    0.56
    verifyException
    0.56
    haikusbot
    0.55
     مشين
    0.55
    uarts
    0.54
    #+#
    0.54
    Activations Density 0.001%

    No Known Activations