© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14992
    Prev
    Next
    INDEX
    Explanations

    elements of code related to database access and error handling

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

    Code and code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    subscription queries

    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
    $_['
    -0.64
    minecraftforge
    -0.56
     Dalio
    -0.53
    Kjelder
    -0.50
    droje
    -0.49
    cordova
    -0.48
     écou
    -0.47
    hasOwnProperty
    -0.47
     xrange
    -0.46
    spyOn
    -0.45
    POSITIVE LOGITS
    tvguidetime
    0.82
    findpost
    0.70
    gatsby
    0.63
     ChatGPT
    0.60
     initComponents
    0.59
     كومونز
    0.56
    tagext
    0.55
    Revenir
    0.54
    Coordenadas
    0.54
    alagi
    0.54
    Activations Density 0.063%

    No Known Activations