© 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. 22-GEMMASCOPE-RES-16K
    11. 7344
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" and other similar prepositions

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

    "In [some circumstance, fact, essence, etc.]"

    np_acts-logits-general · gemini-2.0-flash

    in fact, in essence, in case

    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
    OLUTION
    -0.64
    ruimte
    -0.64
    erun
    -0.62
    getColumnIndex
    -0.61
     MonoBehaviour
    -0.60
     Lordships
    -0.58
    érience
    -0.58
    parseDouble
    -0.57
    abetta
    -0.57
     snippetHide
    -0.56
    POSITIVE LOGITS
    case
    0.62
     fact
    0.56
    تقاوى
    0.52
    первых
    0.52
     hindsight
    0.51
     general
    0.51
    RuleContext
    0.50
     دى
    0.50
     verdad
    0.50
     there
    0.50
    Activations Density 0.348%

    No Known Activations