© 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. 1-GEMMASCOPE-RES-16K
    6. 8968
    Prev
    Next
    INDEX
    Explanations

    references to measurement or units related to micrometers, microphones, and micelles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IBOutlet
    -0.62
     Roskov
    -0.57
    UnusedPrivate
    -0.54
    glie
    -0.53
    legd
    -0.51
     noDo
    -0.50
     setCode
    -0.49
    chieben
    -0.49
    aarrggbb
    -0.49
    /////////////
    -0.49
    POSITIVE LOGITS
     mic
    0.75
    Xna
    0.70
    fjspx
    0.64
     propOrder
    0.58
    Personendaten
    0.56
    Marketplace
    0.56
     serangga
    0.55
    grill
    0.54
     grill
    0.54
     Mic
    0.52
    Activations Density 1.977%

    No Known Activations