© 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. 6540
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a state or condition, particularly involving the word "in"

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

    "in" at the beginning of a clause

    np_acts-logits-general · gemini-2.0-flash

    in addition, in order, in return, in fact, in summary

    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
     kasarigan
    -0.69
     للاسماء
    -0.67
     мәкал
    -0.64
    NameInMap
    -0.62
    featureID
    -0.60
    djangoproject
    -0.60
    ngdoc
    -0.60
     propOrder
    -0.59
    SerializedName
    -0.56
    Cyfeiriadau
    -0.53
    POSITIVE LOGITS
     contrary
    0.66
     form
    0.63
     nutshell
    0.62
     view
    0.58
    VIAF
    0.56
    Hozzáférés
    0.56
    form
    0.56
    hline
    0.55
    StoryboardSegue
    0.53
     meantime
    0.53
    Activations Density 0.352%

    No Known Activations