© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1304
    Prev
    Next
    INDEX
    Explanations

    relationships and connections between individuals and their experiences

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

    Follows personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    first-person pronouns and possessives

    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
     Majefty
    -0.63
     BoxFit
    -0.59
    avadoc
    -0.55
    PROTOBUF
    -0.54
     Jefus
    -0.53
     XNUMX
    -0.53
    intenant
    -0.52
     Monfieur
    -0.52
     ་་
    -0.52
    omenclature
    -0.51
    POSITIVE LOGITS
     me
    2.32
     myself
    2.11
     comigo
    1.74
     conmigo
    1.71
    myself
    1.70
     mine
    1.69
     ourselves
    1.54
     Myself
    1.49
     ours
    1.48
     my
    1.45
    Activations Density 0.785%

    No Known Activations