© 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. 3-GEMMASCOPE-RES-16K
    6. 877
    Prev
    Next
    INDEX
    Explanations

    complex grammatical structures in Japanese, including conjunctions and phrases indicating relationships or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     de
    -0.54
     H
    -0.53
    思います
    -0.53
    en
    -0.51
    気がします
    -0.49
    a
    -0.48
    er
    -0.47
    getActive
    -0.47
    Parcelable
    -0.47
    -
    -0.47
    POSITIVE LOGITS
    と
    1.54
    脚注の使い方
    1.11
    InputBorder
    1.09
    Према
    1.06
     と
    1.06
    expandindo
    1.05
    verwijspagina
    1.05
    kháu
    1.05
    와
    1.05
    과
    1.04
    Activations Density 0.057%

    No Known Activations