© 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. 2-GEMMASCOPE-RES-16K
    6. 2275
    Prev
    Next
    INDEX
    Explanations

    content related to instruction or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     udaler
    -0.46
    ленную
    -0.43
    тельную
    -0.42
     extra
    -0.42
     ucc
    -0.40
     based
    -0.39
    介绍
    -0.39
     about
    -0.38
     
    -0.38
    скую
    -0.38
    POSITIVE LOGITS
    uxxxx
    0.95
     tuturor
    0.90
    __":
    
    0.87
    einem
    0.85
     neuem
    0.84
     surla
    0.81
     ويكيميديا
    0.80
    álním
    0.79
    EDEFAULT
    0.79
    mapStateToProps
    0.77
    Activations Density 0.025%

    No Known Activations