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. 12445
    Prev
    Next
    INDEX
    Explanations

    terms related to leadership and guidance

    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
     оригіналу
    -0.71
    Géographie
    -0.57
    googleapis
    -0.56
    يكب
    -0.55
     leadership
    -0.55
    Personensuche
    -0.54
    leadership
    -0.53
     DBNull
    -0.52
     rhestr
    -0.51
    loài
    -0.50
    POSITIVE LOGITS
     astray
    1.16
     edge
    0.69
     nowhere
    0.68
    gers
    0.67
     pack
    0.65
    gering
    0.64
     charge
    0.64
    cinogenicity
    0.63
     isolada
    0.59
     scorer
    0.58
    Activations Density 0.115%

    No Known Activations