© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 13457
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names and organizations in various contexts

    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
    הערות
    -0.51
    )++;
    -0.49
     <=",
    -0.49
    Viitteet
    -0.46
    Einzelnachweise
    -0.43
     ddelweddau
    -0.43
     предназна
    -0.43
     đó
    -0.42
    writeFieldEnd
    -0.41
    日閲覧
    -0.41
    POSITIVE LOGITS
     among
    0.92
    among
    0.84
     whom
    0.82
     amongst
    0.81
    whom
    0.79
     (†
    0.76
    whose
    0.72
     whose
    0.69
     who
    0.69
     protégé
    0.68
    Activations Density 0.419%

    No Known Activations