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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 856
    Prev
    Next
    INDEX
    Explanations

    comparisons that imply a disparity in expectations or experiences

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

    Personal pronouns followed by a verb of thought

    np_acts-logits-general · gemini-2.0-flash

    than expected or thought

    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
    +#+
    -0.85
    MessageTagHelper
    -0.72
    enderror
    -0.63
     fotografico
    -0.63
     preghiera
    -0.63
     linguistique
    -0.63
     oublié
    -0.61
     kysy
    -0.60
     BoxDecoration
    -0.60
     chrétiens
    -0.59
    POSITIVE LOGITS
     imagined
    0.69
     anticipated
    0.68
     cherchés
    0.63
     expected
    0.62
     thought
    0.61
     hoped
    0.60
    想像
    0.59
     than
    0.59
     imagine
    0.56
    AccessorTable
    0.55
    Activations Density 0.116%

    No Known Activations