© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8077
    Prev
    Next
    INDEX
    Explanations

    phrases related to business operations and strategic planning

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

    followed by prepositions, commas, or quotes

    np_acts-logits-general · gemini-2.0-flash

    going forward

    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
    stateProvider
    -0.65
    цездатний
    -0.56
     esternos
    -0.56
    HandlerContext
    -0.55
     disambiguazione
    -0.51
    UserScript
    -0.50
     spraw
    -0.50
     Rptr
    -0.50
    routeProvider
    -0.48
    NamedQueries
    -0.48
    POSITIVE LOGITS
     moving
    2.38
     Moving
    2.17
    Moving
    2.16
     going
    2.11
    moving
    2.02
    Going
    1.96
     Going
    1.94
     MOVING
    1.89
     GOING
    1.77
    going
    1.74
    Activations Density 0.370%

    No Known Activations