© 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. 11144
    Prev
    Next
    INDEX
    Explanations

    structured data definitions and relationships in programming or database contexts

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

    legal citations ("Id.")

    np_acts-logits-general · gemini-2.0-flash

    . followed by Id

    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
    بوابة
    -0.48
    statusText
    -0.47
    CategoryName
    -0.45
     estimés
    -0.44
    ストロ
    -0.43
    AccountName
    -0.43
    ########.
    -0.43
    ProductName
    -0.42
     swear
    -0.41
    OrderInfo
    -0.41
    POSITIVE LOGITS
     id
    1.81
     Id
    1.65
     ID
    1.62
    Id
    1.56
    id
    1.56
    ID
    1.53
     IDs
    1.50
     ids
    1.40
     getId
    1.33
    getId
    1.30
    Activations Density 0.519%

    No Known Activations