© 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. 8734
    Prev
    Next
    INDEX
    Explanations

    instances of the word "promise."

    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
     AspNetCore
    -0.70
    KELEY
    -0.70
    tanleria
    -0.68
    MLLoader
    -0.64
     Hayek
    -0.63
    anyahu
    -0.63
    ValueStyle
    -0.63
    fjspx
    -0.60
    IsMutable
    -0.59
    ulex
    -0.59
    POSITIVE LOGITS
     promise
    3.62
     Promise
    3.31
     promises
    3.26
    promise
    3.12
    Promise
    3.04
     Promises
    2.87
     promised
    2.85
    promises
    2.75
    Promises
    2.55
     promesa
    2.50
    Activations Density 0.059%

    No Known Activations