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. 7-GEMMASCOPE-RES-16K
    6. 14603
    Prev
    Next
    INDEX
    Explanations

    mentions of "reality" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Alban
    -0.70
    ographia
    -0.64
    parseFrom
    -0.63
    idopsis
    -0.63
    PON
    -0.63
     Swansea
    -0.60
     Amic
    -0.60
     bacter
    -0.60
     auk
    -0.59
     voie
    -0.58
    POSITIVE LOGITS
     reality
    1.60
     Reality
    1.57
    Reality
    1.52
     realities
    1.41
    reality
    1.40
     realidad
    1.09
     realidade
    1.07
     realty
    1.05
     Truths
    1.04
     réalité
    1.04
    Activations Density 0.085%

    No Known Activations