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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 277
    Prev
    Next
    INDEX
    Explanations

    terms related to data dumping and process identifiers (PIDs)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Gemma cluster 5

    No Comments

    Negative Logits
    TypedDataSet
    -0.73
    yya
    -0.60
    oriasis
    -0.57
     pengh
    -0.56
     nonatomic
    -0.55
     gad
    -0.55
    unque
    -0.55
     Gad
    -0.53
    sedi
    -0.53
    iastes
    -0.52
    POSITIVE LOGITS
     dumps
    1.05
     dump
    1.05
     dumping
    0.93
    dumps
    0.93
     dumped
    0.92
     Dump
    0.87
    Bun
    0.80
    Dump
    0.80
    DUMP
    0.79
     Bun
    0.78
    Activations Density 0.062%

    No Known Activations