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. 24-GEMMASCOPE-RES-16K
    6. 2218
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables related to formal expressions and definitions in equations

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

    Mathematical or algebraic symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.79
     оригіналу
    -0.74
    InjectMocks
    -0.67
    новништво
    -0.61
     initComponents
    -0.60
    WaitGroup
    -0.57
    WithMany
    -0.56
     članak
    -0.56
    mybatisplus
    -0.55
     disambiguazione
    -0.54
    POSITIVE LOGITS
     \
    0.70
     $\
    0.70
     &\
    0.62
    }}}\
    0.61
    $\
    0.59
     â
    0.59
    }}\
    0.58
    })\
    0.57
     app
    0.55
    &\
    0.54
    Activations Density 1.409%

    No Known Activations