© 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. 20-GEMMASCOPE-RES-16K
    6. 5675
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility, necessity, or future actions

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

    preceding future tense auxiliaries

    np_acts-logits-general · gemini-2.0-flash

    what something means will happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InvalidProtocol
    -0.65
    yntaxException
    -0.62
    RetentionPolicy
    -0.58
    SharedDtor
    -0.56
    UrlResolution
    -0.53
     nori
    -0.52
    CppCodeGen
    -0.52
    antMatchers
    -0.51
     BorderSide
    -0.51
    Personendaten
    -0.50
    POSITIVE LOGITS
     mean
    0.80
    mean
    0.71
     MEAN
    0.69
     Mean
    0.65
     bedeuten
    0.63
    Mean
    0.63
    TagMode
    0.62
    Interess
    0.62
     solves
    0.62
    MEAN
    0.60
    Activations Density 0.297%

    No Known Activations