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. 5-GEMMASCOPE-RES-16K
    6. 5445
    Prev
    Next
    INDEX
    Explanations

    references to storytelling or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Félix
    -0.78
    人民共和国
    -0.77
    principalColumn
    -0.75
     velours
    -0.74
    ##############
    -0.68
    cstdlib
    -0.68
     سكانية
    -0.68
    ihnachten
    -0.68
    ภัณฑ์
    -0.67
    bbene
    -0.66
    POSITIVE LOGITS
     story
    2.42
     stories
    2.26
     Story
    2.17
    Story
    2.06
    story
    2.05
     STORY
    1.99
     Stories
    1.94
    Stories
    1.86
    stories
    1.75
    STORY
    1.73
    Activations Density 0.032%

    No Known Activations