© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 15151
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and personal struggles

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

    Third-person pronouns followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns and 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parcelize
    -0.64
     families
    -0.50
     Deh
    -0.48
     *__
    -0.48
     initComponents
    -0.47
    propTypes
    -0.46
     VU
    -0.46
     ***!
    -0.45
     useDispatch
    -0.45
    lwjgl
    -0.44
    POSITIVE LOGITS
    WebElementEntity
    0.76
     <=",
    0.58
    lossians
    0.56
     himself
    0.54
    verifyException
    0.54
    himself
    0.53
     HasFactory
    0.52
    rån
    0.52
     Walkover
    0.51
     his
    0.50
    Activations Density 0.300%

    No Known Activations