© 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. 6111
    Prev
    Next
    INDEX
    Explanations

    terms related to awareness and understanding

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

    Forms of the word "recognize"

    np_acts-logits-general · gemini-2.0-flash

    recognize

    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
     hoffen
    -0.54
     отношению
    -0.53
    помним
    -0.53
    leby
    -0.52
    doi
    -0.51
    ://
    -0.51
    odendron
    -0.50
     razie
    -0.50
    tover
    -0.49
    claimer
    -0.49
    POSITIVE LOGITS
     recognise
    0.76
    '));
    
    0.75
     StringTokenizer
    0.74
     flaws
    0.73
     recognising
    0.70
     recognises
    0.70
     LoggerFactory
    0.69
     recognition
    0.68
    ]';
    0.68
    ()));
    
    0.68
    Activations Density 0.252%

    No Known Activations