© 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. 15-GEMMASCOPE-RES-16K
    6. 13524
    Prev
    Next
    INDEX
    Explanations

    references to event handlers or callback functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIAF
    -0.63
    omla
    -0.61
    -------
    -0.60
     clearColor
    -0.57
    сторія
    -0.56
    
    -0.54
     teratur
    -0.53
    ecake
    -0.52
     UnityEditor
    -0.52
     FixedUpdate
    -0.51
    POSITIVE LOGITS
    sender
    1.25
     sender
    1.18
     Sender
    1.02
    Sender
    0.88
     discri
    0.69
     Efq
    0.69
    GetKeyDown
    0.65
     Lender
    0.64
    SequentialGroup
    0.63
     Mathi
    0.62
    Activations Density 0.040%

    No Known Activations