© 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. 18-GEMMASCOPE-RES-16K
    11. 11372
    Prev
    Next
    INDEX
    Explanations

    mentions of personal relationships and family dynamics

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

    Followed by personal pronouns or names

    np_acts-logits-general · gemini-2.0-flash

    people and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     =>
    -0.59
    XmlRootElement
    -0.57
    NOPQRST
    -0.56
     mármol
    -0.56
     विश्वसनीयता
    -0.54
    RefNanny
    -0.53
     ligiloj
    -0.52
    InitStructure
    -0.51
     кӀ
    -0.49
    ddha
    -0.48
    POSITIVE LOGITS
     insisted
    0.74
    WebElementEntity
    0.69
     GenerationType
    0.67
     оригіналу
    0.66
     "..\..\..\
    0.61
    RotationOrder
    0.59
     suggestion
    0.57
    ніципалі
    0.56
     lead
    0.55
     spear
    0.55
    Activations Density 0.256%

    No Known Activations