© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 1850
    Prev
    Next
    INDEX
    Explanations

    statements about the state of things or feelings, particularly reflections on experiences and situations

    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
    Autoritní
    -0.70
    出版年
    -0.67
     ivelany
    -0.64
     betweenstory
    -0.63
     Sensation
    -0.63
     subgoal
    -0.63
    databind
    -0.62
     AspNetCore
    -0.60
     ChromeDriver
    -0.59
    nationality
    -0.59
    POSITIVE LOGITS
     a
    0.72
     important
    0.66
     real
    0.55
     something
    0.54
     part
    0.54
     an
    0.52
     different
    0.51
     not
    0.51
     difficult
    0.50
     hard
    0.48
    Activations Density 0.144%

    No Known Activations