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. 23-GEMMASCOPE-RES-16K
    6. 9026
    Prev
    Next
    INDEX
    Explanations

    different types of function calls or expressions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }}}{\
    -0.67
     """
    
    -0.65
    "){
    
    -0.64
     pleaſure
    -0.63
     écout
    -0.62
     myſelf
    -0.62
    ),"
    -0.61
     hâte
    -0.61
     purpoſe
    -0.61
    )}_
    -0.59
    POSITIVE LOGITS
     =>
    1.70
    =>
    1.13
     =>'
    0.91
    =>"
    0.88
    =>'
    0.81
    =>$
    0.80
     <=>
    0.77
     =>
    
    0.76
     =>{
    0.76
    Rightarrow
    0.72
    Activations Density 0.053%

    No Known Activations