© 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. 20-GEMMASCOPE-RES-16K
    6. 83
    Prev
    Next
    INDEX
    Explanations

    terms related to linear functions and their properties

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

    Following "linear"

    np_acts-logits-general · gemini-2.0-flash

    linear functions and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.83
     resourceCulture
    -0.72
    CppMethod
    -0.65
    })();
    
    -0.58
    IInterface
    -0.57
     AssemblyProduct
    -0.56
    Ecotoxicity
    -0.55
    SharedCtor
    -0.54
     onPostExecute
    -0.54
    })()
    -0.53
    POSITIVE LOGITS
    ization
    0.77
    ity
    0.72
    ized
    0.66
    isation
    0.64
    izing
    0.61
    ATIVO
    0.60
     programming
    0.59
     regression
    0.58
     recl
    0.56
    BagLayout
    0.56
    Activations Density 0.183%

    No Known Activations