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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4410
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and decisions

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

    Follows a name or pronoun, precedes "said" or "stated"

    np_acts-logits-general · gemini-2.0-flash

    verbs of saying

    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
    interopRequire
    -0.83
    +#+
    -0.73
     Monfieur
    -0.70
    Rhestr
    -0.70
    AddTagHelper
    -0.68
     насељу
    -0.66
    StructEnd
    -0.64
     оригіналу
    -0.63
    SBATCH
    -0.62
    adaptiveStyles
    -0.60
    POSITIVE LOGITS
     said
    1.22
     berkata
    1.14
    Said
    1.07
     says
    1.06
     saying
    1.04
     Says
    1.00
     Said
    0.98
    said
    0.98
     stated
    0.96
    Says
    0.93
    Activations Density 0.444%

    No Known Activations