© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 628
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or terms related to calculus and derivatives

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

    mathematical expressions or operations

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

    mathematical expressions, code syntax

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     EconPapers
    -0.67
    parsedMessage
    -0.65
    Pyx
    -0.60
     оригіналу
    -0.56
     protoimpl
    -0.55
    hesis
    -0.51
    domo
    -0.51
    DeleteBehavior
    -0.50
     PyTuple
    -0.50
    ConverterFactory
    -0.48
    POSITIVE LOGITS
     Normdatei
    0.70
    bilirsiniz
    0.56
    "]="
    0.56
    ptonshire
    0.55
    })));
    0.55
    новништво
    0.54
    ']='
    0.53
     éner
    0.53
     vettore
    0.53
    zież
    0.50
    Activations Density 0.570%

    No Known Activations