© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 58783
    Prev
    Next
    INDEX
    Explanations

    references to binding and bound states, particularly in programming or licensing contexts

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

    bind, bound, binding

    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
     المعيارى
    -0.70
     kasarigan
    -0.57
     noDo
    -0.55
     surla
    -0.55
    UserScript
    -0.55
     незавершена
    -0.54
    AndEndTag
    -0.51
    styleType
    -0.51
    Geplaatst
    -0.51
    +:+
    -0.49
    POSITIVE LOGITS
     binding
    1.31
     bound
    1.27
     bind
    1.26
     Binding
    1.25
     Bind
    1.22
     Bound
    1.17
     binds
    1.15
     bindings
    1.13
    Bind
    1.13
     BIND
    1.12
    Activations Density 0.071%

    No Known Activations