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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7670
    Prev
    Next
    INDEX
    Explanations

    programming terminology and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     чому
    -0.39
    OrCreate
    -0.37
     sentidos
    -0.37
    avajillas
    -0.36
     fronteras
    -0.35
     żel
    -0.35
     Ensino
    -0.34
     proceeds
    -0.34
     bacio
    -0.34
     învă
    -0.34
    POSITIVE LOGITS
    ftagPool
    0.75
    bootstrapcdn
    0.68
     SqlDbType
    0.67
     surla
    0.61
    fjspx
    0.60
     CreateTagHelper
    0.60
     الحره
    0.59
    haikusbot
    0.58
    AddTagHelper
    0.58
    addContainerGap
    0.57
    Activations Density 0.634%

    No Known Activations