© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8760
    Prev
    Next
    INDEX
    Explanations

    function calls and method invocations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -0.55
     CONTRIBUTION
    -0.48
     Flü
    -0.47
     Meilleures
    -0.47
     logr
    -0.45
    HasBeenSet
    -0.44
    "",
    
    -0.44
     intervenir
    -0.44
     intervened
    -0.43
     fjer
    -0.43
    POSITIVE LOGITS
    get
    0.90
     betweenstory
    0.52
     get
    0.49
     "..\..\..\
    0.47
    epam
    0.47
    teman
    0.44
     AssemblyTitle
    0.43
    AddTagHelper
    0.42
    $_['
    0.42
    ToScroll
    0.41
    Activations Density 0.107%

    No Known Activations