© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5665
    Prev
    Next
    INDEX
    Explanations

    responses that indicate a solution or answer to a question

    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
    NewUrlParser
    -0.75
    LLocation
    -0.68
     CreateTagHelper
    -0.60
     بيها
    -0.56
    FXMLLoader
    -0.54
    AutoField
    -0.54
    Према
    -0.53
    cokinetics
    -0.52
    cokinetic
    -0.50
     насељу
    -0.49
    POSITIVE LOGITS
     answer
    1.44
     solution
    1.43
     Solution
    1.42
     Answer
    1.41
    ANSWER
    1.37
    Solution
    1.37
     answers
    1.34
    solution
    1.34
     ANSWER
    1.31
    Answer
    1.31
    Activations Density 0.342%

    No Known Activations