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. 13-GEMMASCOPE-RES-16K
    6. 6751
    Prev
    Next
    INDEX
    Explanations

    tokens that represent mathematical or scientific notation

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

    mathematical or programming constructs related to variable declarations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.72
    nexo
    -0.67
     
    -0.65
     }
    -0.63
     kid
    -0.62
     Иль
    -0.62
    "
    -0.62
    MethodManager
    -0.60
     el
    -0.60
     E
    -0.59
    POSITIVE LOGITS
     (\<
    1.08
     myſelf
    1.04
    ſelves
    1.04
     (§
    1.01
     actionMode
    1.01
     itſelf
    0.99
    (\
    0.98
     Kaufmann
    0.97
     Anſ
    0.96
    {(\
    0.96
    Activations Density 0.565%

    No Known Activations