Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9283
    Prev
    Next
    INDEX
    Explanations

    temporal and scheduling references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.65
     Amongst
    -0.59
    Whilst
    -0.57
     Whilst
    -0.57
     amongst
    -0.55
     whilst
    -0.48
    ियाँ
    -0.45
    __(/*!
    -0.43
     EconPapers
    -0.42
     exciting
    -0.42
    POSITIVE LOGITS
     CURIAM
    0.58
    #+#
    0.57
    
    0.53
    LabelTagHelper
    0.53
    الدراسه
    0.52
    Assured
    0.49
    stateParams
    0.49
     Sept
    0.48
    . 
    0.48
     <=",
    0.47
    Activations Density 0.161%

    No Known Activations