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. 12-GEMMASCOPE-RES-16K
    6. 61
    Prev
    Next
    INDEX
    Explanations

    phrases indicating alternative options or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.93
    dymyr
    -0.87
    #+#
    -0.80
    mPaint
    -0.73
    dasarkan
    -0.72
    arithmic
    -0.71
    kadot
    -0.71
     télévis
    -0.70
     sientes
    -0.70
     vostri
    -0.69
    POSITIVE LOGITS
     Alternative
    1.65
    Alternative
    1.65
     alternatives
    1.64
     alternative
    1.63
     Alternatives
    1.54
    Alternatives
    1.50
     ALTERNATIVE
    1.42
     ALTERN
    1.36
     altern
    1.34
    alternative
    1.33
    Activations Density 0.079%

    No Known Activations