© 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. 11337
    Prev
    Next
    INDEX
    Explanations

    references to statistical analysis and risk in business contexts

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

    preceding expressions of uncertainty

    np_acts-logits-general · gemini-2.0-flash

    probability and likelihood

    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
    føl
    -0.53
    なんです
    -0.47
    なんですよ
    -0.47
    Geografi
    -0.46
    UTRAL
    -0.44
     протяжении
    -0.43
    anii
    -0.41
    なのです
    -0.41
    벗
    -0.40
    なんですが
    -0.40
    POSITIVE LOGITS
     probably
    3.44
    probably
    3.18
     Probably
    3.10
    Probably
    3.04
     likely
    2.89
     doubtless
    2.63
     probabilmente
    2.58
    likely
    2.58
     probablemente
    2.52
     provavelmente
    2.50
    Activations Density 1.455%

    No Known Activations