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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 939
    Prev
    Next
    INDEX
    Explanations

    references to pricing and related numeric data in context

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

    after a quotation mark or apostrophe

    np_acts-logits-general · gemini-2.0-flash

    next to be read

    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
    StoryboardSegue
    -0.69
    IUrlHelper
    -0.68
    Personensuche
    -0.65
    Trama
    -0.65
     BorderRadius
    -0.63
     bezeichneter
    -0.63
     ExecuteAsync
    -0.62
    RefNanny
    -0.61
    expandindo
    -0.60
    ownload
    -0.59
    POSITIVE LOGITS
     let
    0.62
     I
    0.62
     comigo
    0.62
     dont
    0.61
    ようになりました
    0.59
     don
    0.59
     do
    0.58
     not
    0.57
     Get
    0.57
    smarty
    0.56
    Activations Density 0.342%

    No Known Activations