Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 1861
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions surrounding the idea of "reality."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.74
     CreateTagHelper
    -0.73
    URIComponent
    -0.65
    labus
    -0.63
    idigung
    -0.60
    MatButtonModule
    -0.59
    posium
    -0.56
    gypti
    -0.56
     defaultstate
    -0.56
    manship
    -0.53
    POSITIVE LOGITS
    Reality
    1.04
     Reality
    1.02
     reality
    0.93
     realities
    0.91
    reality
    0.89
     réal
    0.86
    REAL
    0.80
     realty
    0.76
     réalité
    0.75
     REAL
    0.73
    Activations Density 0.087%

    No Known Activations