© 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. 4-GEMMASCOPE-RES-16K
    6. 16143
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss conditions or situations that can change based on certain factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.63
    thâu
    -0.60
    Referències
    -0.57
     Horst
    -0.56
     John
    -0.55
     ioutil
    -0.55
     Rad
    -0.54
    oblastoma
    -0.53
     Bradbury
    -0.52
    dflare
    -0.51
    POSITIVE LOGITS
     depending
    2.50
    depending
    2.40
     Depending
    2.25
    Depending
    2.23
     Depends
    1.89
     dependiendo
    1.79
     depends
    1.75
    depends
    1.73
    Depends
    1.65
     depended
    1.56
    Activations Density 0.104%

    No Known Activations