© 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. 24-GEMMASCOPE-RES-16K
    11. 4123
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to value and importance in various contexts

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

    Sentences referencing importance or relevance

    np_acts-logits-general · gemini-2.0-flash

    what matters

    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
    èdia
    -0.71
    AntiForgeryToken
    -0.56
    czej
    -0.52
    GTCX
    -0.51
    PONSE
    -0.51
     voici
    -0.51
    도록
    -0.50
    spyOn
    -0.49
     '__
    -0.48
     RSSSF
    -0.48
    POSITIVE LOGITS
     matters
    2.35
     matter
    2.33
     mattered
    2.07
    matters
    2.00
    matter
    1.98
     Matters
    1.93
     MATTER
    1.92
     Matter
    1.91
     MATTERS
    1.90
    Matters
    1.79
    Activations Density 0.257%

    No Known Activations