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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11368
    Prev
    Next
    INDEX
    Explanations

    function and method calls associated with geometric and mathematical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    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
    -0.53
    oa̍t
    -0.47
    xase
    -0.46
    IVEREF
    -0.45
    contentLoaded
    -0.44
    yntaxException
    -0.42
    ANTLR
    -0.41
     الحره
    -0.41
    sbericht
    -0.40
     fontSize
    -0.40
    POSITIVE LOGITS
     +
    1.14
    +
    1.07
    +
    0.93
     plus
    0.91
     $+
    0.85
     плюс
    0.80
     + 
    0.80
    +\
    0.77
     $+$
    0.77
     minus
    0.75
    Activations Density 2.279%

    No Known Activations