Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10945
    Prev
    Next
    INDEX
    Explanations

    gerunds and present participles describing actions

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

    preceding a gerund

    np_acts-logits-general · gemini-2.0-flash

    words ending in ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INGS
    -0.51
    ings
    -0.47
    IVENESS
    -0.47
    ContentAlignment
    -0.47
    giv
    -0.46
    zame
    -0.46
    collana
    -0.46
    duino
    -0.45
    taken
    -0.45
     VIAF
    -0.44
    POSITIVE LOGITS
     nahilalakip
    0.93
    findpost
    0.88
    DeleteBehavior
    0.81
     "..\..\..\
    0.70
     "..\..\
    0.70
     ostavi
    0.70
    LookAnd
    0.67
    Personendaten
    0.66
     ProtoMessage
    0.66
    AndroidJUnit
    0.65
    Activations Density 0.220%

    No Known Activations