© 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. 22-GEMMASCOPE-RES-16K
    11. 10577
    Prev
    Next
    INDEX
    Explanations

    concepts related to understanding and analyzing the implications of information or events

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

    Definition or meaning of something

    np_acts-logits-general · gemini-2.0-flash

    what it means

    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
     vectorielle
    -0.53
     Portail
    -0.52
     fiind
    -0.51
    JoinTable
    -0.51
     rimanere
    -0.50
     Shouldn
    -0.50
    Shouldn
    -0.49
    InlineData
    -0.48
     shouldn
    -0.48
    Portail
    -0.48
    POSITIVE LOGITS
     entail
    0.94
     entails
    0.94
     entailed
    0.83
    awtextra
    0.74
     really
    0.71
     actually
    0.69
     exactly
    0.68
    到底
    0.64
     ACTUALLY
    0.64
    GOTREF
    0.63
    Activations Density 0.142%

    No Known Activations