Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 6607
    Prev
    Next
    INDEX
    Explanations

    references to production details and insights related to filmmaking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    music or acting

    np_acts-logits-general · gemini-2.0-flash

    production and media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.58
    apunov
    -0.57
    出版年
    -0.57
    principalTable
    -0.56
    SequentialGroup
    -0.56
     Roskov
    -0.53
    μως
    -0.50
     cív
    -0.49
     GLFW
    -0.49
     prefixes
    -0.48
    POSITIVE LOGITS
     studio
    1.02
     rehearsals
    0.96
     backstage
    0.91
     production
    0.91
     audition
    0.86
     rehearsal
    0.84
     Studios
    0.83
     studios
    0.83
     filming
    0.83
     Production
    0.82
    Activations Density 0.278%

    No Known Activations