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. 22-GEMMASCOPE-RES-16K
    6. 8046
    Prev
    Next
    INDEX
    Explanations

    molecular terms and concepts related to apoptosis and signaling pathways

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

    Biological or chemical mechanisms/pathways

    np_acts-logits-general · gemini-2.0-flash

    regulation via mechanisms and pathways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.78
     nakalista
    -0.63
    contentLoaded
    -0.55
     Browne
    -0.53
     sabar
    -0.52
     становника
    -0.52
     swab
    -0.52
     kiệm
    -0.51
    RetentionPolicy
    -0.50
    kiwa
    -0.50
    POSITIVE LOGITS
     regulation
    1.19
     mechanisms
    1.12
     mechanism
    1.09
     regulating
    1.05
     regulate
    1.04
    regulation
    1.00
     regulates
    0.98
     Regulation
    0.98
     Mechanisms
    0.98
     Mechanism
    0.97
    Activations Density 2.997%

    No Known Activations