© 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. 16-GEMMASCOPE-RES-16K
    11. 13076
    Prev
    Next
    INDEX
    Explanations

    connections between problems and proposed solutions or methods to address them

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

    Preceding the word "this"

    np_acts-logits-general · gemini-2.0-flash

    overcome this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bolo
    -0.50
     Google
    -0.44
    Hauptartikel
    -0.43
     $)
    -0.40
    stot
    -0.40
     ();
    -0.40
    tagHelperRunner
    -0.40
    adal
    -0.39
    Doodle
    -0.39
    ItemSelected
    -0.39
    POSITIVE LOGITS
     this
    1.30
     these
    1.20
     such
    1.14
    Such
    1.00
     solcher
    0.99
    such
    0.96
     theſe
    0.96
     Such
    0.94
     چنین
    0.94
     solchen
    0.93
    Activations Density 0.881%

    No Known Activations