© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7265
    Prev
    Next
    INDEX
    Explanations

    results, outcomes, and findings from studies or analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding reports of results/outcomes

    np_acts-logits-general · gemini-2.0-flash

    study results and conclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yarnpkg
    -0.69
    tvguidetime
    -0.66
     виправивши
    -0.65
     AssemblyVersion
    -0.65
     UITableViewCell
    -0.62
    Pautan
    -0.60
     незавершена
    -0.60
     ComVisible
    -0.59
     MatDialog
    -0.59
    WriteAttribute
    -0.58
    POSITIVE LOGITS
     onPostExecute
    0.65
     results
    0.63
     outcomes
    0.60
     erzielt
    0.59
     Results
    0.58
     Outcomes
    0.56
     Ergebnis
    0.56
     esperado
    0.56
    outcomes
    0.56
    Results
    0.56
    Activations Density 0.518%

    No Known Activations