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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 57756
    Prev
    Next
    INDEX
    Explanations

    function calls related to setting adapters in a user interface

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

    setAdapter, getAdapter, Adapter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.43
     يتيمه
    -0.40
    sterious
    -0.38
    Ārējās
    -0.37
    dchen
    -0.36
    ð
    -0.35
     kaarangay
    -0.34
    enschaften
    -0.33
    帖最后由
    -0.33
    ricians
    -0.32
    POSITIVE LOGITS
    setAdapter
    4.31
    BaseAdapter
    1.00
    setLayoutManager
    0.94
    getAdapter
    0.90
    Adapter
    0.88
     Adapter
    0.88
     adapter
    0.82
    adapter
    0.80
    adaptador
    0.80
     Adap
    0.79
    Activations Density 0.000%

    No Known Activations