© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15337
    Prev
    Next
    INDEX
    Explanations

    terms related to binding and connections

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

    "bind" or "bound" and related words

    np_acts-logits-general · gemini-2.0-flash

    bind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.84
    DockStyle
    -0.77
    GraphicsUnit
    -0.74
    abestanden
    -0.69
    adaptiveStyles
    -0.68
     betweenstory
    -0.66
     EconPapers
    -0.64
     noten
    -0.62
    twimg
    -0.62
    viewDidLoad
    -0.62
    POSITIVE LOGITS
     Bind
    0.89
     binds
    0.86
     BIND
    0.84
    IBinder
    0.84
     binding
    0.79
     bind
    0.78
    bindValue
    0.78
     bindings
    0.76
     Binding
    0.75
    binding
    0.71
    Activations Density 0.124%

    No Known Activations