© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13120
    Prev
    Next
    INDEX
    Explanations

    phrases that describe interpersonal conflict and problematic behaviors in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPATH
    -0.59
     ProtoMessage
    -0.56
    出版年
    -0.56
    WebElementEntity
    -0.56
     ujednoznacz
    -0.54
    RotationOrder
    -0.51
     Signalez
    -0.48
    IsContent
    -0.45
    InputTagHelper
    -0.45
    }{*}{
    -0.44
    POSITIVE LOGITS
    Encyklopedia
    0.37
     defaultdict
    0.36
     Stimmung
    0.36
    woven
    0.35
    nement
    0.34
    artig
    0.34
    ban
    0.34
    windowFixed
    0.33
    outcome
    0.33
    Rozm
    0.33
    Activations Density 0.126%

    No Known Activations