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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10619
    Prev
    Next
    INDEX
    Explanations

    phrases related to control and dependency issues

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

    "control" or words preceding "control"

    np_acts-logits-general · gemini-2.0-flash

    control

    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
     <>",
    -0.48
    PageFactory
    -0.47
     FetchType
    -0.46
     AsyncTask
    -0.46
    AutoField
    -0.44
     letter
    -0.43
     minOccurs
    -0.43
    ANDUM
    -0.42
     Ladd
    -0.42
    INAS
    -0.42
    POSITIVE LOGITS
     control
    3.87
     Control
    3.45
    control
    3.44
    Control
    3.24
     CONTROL
    3.20
    CONTROL
    2.98
     contrôle
    2.81
     controls
    2.81
     controle
    2.78
     controlling
    2.75
    Activations Density 0.699%

    No Known Activations