© 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. 18-GEMMASCOPE-RES-16K
    11. 3273
    Prev
    Next
    INDEX
    Explanations

    references to decisions, actions, and their repercussions, particularly in legal and procedural contexts

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

    achievements or progress ("gains")

    np_acts-logits-general · gemini-2.0-flash

    past gains and previous accomplishments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodedInputStream
    -0.56
    횟
    -0.55
     MenuView
    -0.54
    hoppers
    -0.53
    Vary
    -0.50
    thalt
    -0.49
    alai
    -0.49
     {}),
    -0.49
    Deskripsi
    -0.47
     propose
    -0.47
    POSITIVE LOGITS
     gains
    1.03
     momentum
    0.90
    好不容易
    0.88
     achievements
    0.86
     already
    0.81
     previously
    0.80
    gains
    0.79
     previous
    0.79
    already
    0.77
     accomplishments
    0.76
    Activations Density 0.469%

    No Known Activations