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. 19-GEMMASCOPE-RES-16K
    6. 415
    Prev
    Next
    INDEX
    Explanations

    statements reflecting personal beliefs and motivations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hans
    -0.49
    our
    -0.48
    ixx
    -0.48
    师
    -0.47
     mūsų
    -0.45
     A
    -0.45
     mich
    -0.45
     the
    -0.44
    kenalkan
    -0.44
    phos
    -0.44
    POSITIVE LOGITS
    ValueStyle
    1.18
    帖最后由
    1.15
     EconPapers
    1.14
     ujednoznacz
    1.13
     resourceCulture
    1.08
    ScopeManager
    1.07
    StoryboardSegue
    1.06
    Datuak
    1.03
    tagHelperRunner
    1.02
     ligiloj
    1.01
    Activations Density 1.090%

    No Known Activations