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. 8576
    Prev
    Next
    INDEX
    Explanations

    complex structures and hierarchical data formats, likely related to JSON or structured programming elements

    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
     Jaffe
    -0.59
    tiff
    -0.59
    AndEndTag
    -0.58
     виправивши
    -0.55
    帖最后由
    -0.55
     Llew
    -0.54
     jsonify
    -0.53
    thâu
    -0.51
     Afghanistan
    -0.51
     DJI
    -0.51
    POSITIVE LOGITS
                  
    1.15
    ValueStyle
    0.65
     henvisninger
    0.58
    rrggbb
    0.54
     Signalez
    0.52
    GEBURTSDATUM
    0.50
    राम
    0.50
    écart
    0.48
     intptr
    0.48
    Билгалдахарш
    0.47
    Activations Density 0.072%

    No Known Activations