© 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. 5584
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "InstanceState" within the context of programming and state management

    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
    addCriterion
    -1.30
    StoryboardSegue
    -0.70
     autorytatywna
    -0.67
     ""],
    -0.67
    addGroup
    -0.67
    Démographie
    -0.66
    تفصیلات
    -0.61
     petty
    -0.60
    êtement
    -0.59
    鰭
    -0.59
    POSITIVE LOGITS
    enumi
    2.58
    tagHelper
    2.12
    enumii
    1.46
    InstanceState
    1.00
    jPanel
    0.97
    bibitem
    0.84
    
    0.68
    DebuggerNonUser
    0.68
    SequentialGroup
    0.67
    </thead>
    0.67
    Activations Density 0.002%

    No Known Activations