© 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. 5-GEMMASCOPE-RES-16K
    6. 6419
    Prev
    Next
    INDEX
    Explanations

    concepts related to evaluation or comparison of quantities and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yoshida
    -0.70
     Elo
    -0.64
     riso
    -0.62
     Hayes
    -0.61
     model
    -0.60
     McCarthy
    -0.60
     same
    -0.60
     Claude
    -0.59
    +'</
    -0.59
     angle
    -0.59
    POSITIVE LOGITS
     consultato
    0.90
     presso
    0.85
     את
    0.81
     ristoranti
    0.79
     the
    0.79
     attraverso
    0.79
     notizia
    0.78
    GraphicsUnit
    0.77
     ezt
    0.77
     getopt
    0.75
    Activations Density 0.405%

    No Known Activations