© 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. 18-GEMMASCOPE-RES-16K
    6. 3338
    Prev
    Next
    INDEX
    Explanations

    phrases related to mechanical instructions and assembly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Action of inserting or pushing something

    np_acts-logits-general · gemini-2.0-flash

    insert into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onCancelled
    -0.53
     ujednoznacz
    -0.47
    ządz
    -0.45
     Exactos
    -0.44
    émission
    -0.44
     vieill
    -0.44
    RUnlock
    -0.43
     métallique
    -0.43
     initComponents
    -0.43
    writeField
    -0.42
    POSITIVE LOGITS
     postData
    0.61
     插入
    0.60
     insert
    0.59
     ContentValues
    0.58
    插入
    0.56
     pushed
    0.56
     push
    0.56
    InsertCommand
    0.55
    insert
    0.54
    AntiForgeryToken
    0.54
    Activations Density 0.166%

    No Known Activations