© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2984
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to solving problems and providing support

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

    after "the"

    np_acts-logits-general · gemini-2.0-flash

    relieve stress

    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
    帖最后由
    -0.62
    DockStyle
    -0.57
    extAlignment
    -0.56
    Personensuche
    -0.54
    脚注の使い方
    -0.53
    TProtocol
    -0.52
     aDecoder
    -0.51
     Meksiku
    -0.48
     Byzantium
    -0.48
     mycelium
    -0.48
    POSITIVE LOGITS
     relieves
    1.21
     relieve
    1.19
     relieving
    1.09
     relieved
    1.05
     frees
    1.02
     freeing
    1.02
     relief
    0.99
     stress
    0.97
    Relief
    0.95
     alleviate
    0.93
    Activations Density 0.189%

    No Known Activations