© 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. 24-GEMMASCOPE-RES-16K
    6. 2025
    Prev
    Next
    INDEX
    Explanations

    scientific and chemical terminology related to reactions and synthesis processes

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

    Follows "substituted"

    np_acts-logits-general · gemini-2.0-flash

    synthesis of amines and related compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.51
     Référence
    -0.51
     nonatomic
    -0.50
    abestanden
    -0.50
    ombic
    -0.49
    Subviews
    -0.49
     ambul
    -0.47
    Externé
    -0.46
    पया
    -0.46
     crawl
    -0.46
    POSITIVE LOGITS
    tagHelperRunner
    0.81
     amine
    0.62
    agisse
    0.60
     amines
    0.59
    antMatchers
    0.57
     alcoholic
    0.53
     alkoh
    0.52
    mybatisplus
    0.51
     kasarigan
    0.50
    keti
    0.50
    Activations Density 0.792%

    No Known Activations