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. 25-GEMMASCOPE-RES-16K
    6. 7310
    Prev
    Next
    INDEX
    Explanations

    patterns and symbols used in programming, particularly related to structures and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الوطنيه
    -0.55
    исленность
    -0.53
    /*
    -0.51
    Personensuche
    -0.50
    /**
    -0.49
    assword
    -0.49
     certify
    -0.49
     Witten
    -0.49
    sizable
    -0.48
     benne
    -0.48
    POSITIVE LOGITS
     this
    0.87
    this
    0.83
     self
    0.77
    self
    0.74
     dAtA
    0.64
     &_
    0.63
    Self
    0.63
     Self
    0.60
    ));
    
    0.58
     resourceCulture
    0.58
    Activations Density 0.804%

    No Known Activations