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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7959
    Prev
    Next
    INDEX
    Explanations

    code elements and functions related to rendering in a web application context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ligiloj
    -0.45
    期刊论文
    -0.42
     unknownFields
    -0.41
    TableBody
    -0.41
    ""}
    -0.38
    ⎦
    -0.37
    PhysRev
    -0.36
     otomatig
    -0.36
     Semin
    -0.35
     Simons
    -0.35
    POSITIVE LOGITS
     express
    0.65
     bodyParser
    0.61
     middleware
    0.61
     Express
    0.60
    express
    0.59
    Express
    0.58
     Middleware
    0.58
    EXPRESS
    0.56
     expres
    0.53
     router
    0.51
    Activations Density 0.145%

    No Known Activations