Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14129
    Prev
    Next
    INDEX
    Explanations

    discussions about processes, decisions, or recommendations related to rules, governance, and social or corporate issues

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

    Follows modal verbs

    np_acts-logits-general · gemini-2.0-flash

    modal verbs followed by actions

    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
     mourut
    -1.08
     étoit
    -1.04
     médicaux
    -0.97
     auroit
    -0.94
     giudi
    -0.94
     actuels
    -0.91
     normaux
    -0.89
     épis
    -0.88
     exceptionnelle
    -0.87
     feroit
    -0.87
    POSITIVE LOGITS
     build
    1.05
     use
    1.03
     take
    1.02
     make
    1.02
     pick
    1.01
     create
    0.99
     turn
    0.98
     draw
    0.98
     move
    0.97
     push
    0.96
    Activations Density 3.463%

    No Known Activations