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. 8434
    Prev
    Next
    INDEX
    Explanations

    references to financial organizations and their activities

    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
    URLException
    -0.70
    rungsseite
    -0.69
    الحياه
    -0.66
    rupal
    -0.63
     kaynağından
    -0.62
     xlink
    -0.60
    Companies
    -0.59
     समीक्षक
    -0.58
    PRWEB
    -0.56
     Companies
    -0.56
    POSITIVE LOGITS
    mult
    0.70
     majors
    0.70
     major
    0.69
     mult
    0.67
     multinational
    0.65
     giant
    0.64
     behe
    0.62
    major
    0.60
    maj
    0.59
     Fortune
    0.59
    Activations Density 0.312%

    No Known Activations