© 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. 919
    Prev
    Next
    INDEX
    Explanations

    references to individuals, particularly in speaking contexts

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

    Follows a person's name or pronoun, plus "added"

    np_acts-logits-general · gemini-2.0-flash

    added information from sources

    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
    ParallelGroup
    -0.57
    AddTagHelper
    -0.56
     Италијани
    -0.56
    findpost
    -0.56
    +#+#
    -0.55
    Enllaces
    -0.53
     виправивши
    -0.52
     CreateTagHelper
    -0.52
     AssemblyCulture
    -0.52
    >//
    -0.52
    POSITIVE LOGITS
     added
    2.20
     adds
    2.03
     add
    1.97
     adding
    1.97
     Added
    1.82
    added
    1.81
     Adding
    1.77
     Adds
    1.76
    Adding
    1.73
     ADDED
    1.72
    Activations Density 0.226%

    No Known Activations