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. 3-GEMMASCOPE-RES-16K
    6. 12950
    Prev
    Next
    INDEX
    Explanations

    instances of options or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.74
     HomeComponent
    -0.68
    urier
    -0.65
    tagHelperRunner
    -0.65
    onenumber
    -0.65
     BIBSYS
    -0.65
    Aholisi
    -0.64
    erializer
    -0.64
    BoxShadow
    -0.63
    Thur
    -0.61
    POSITIVE LOGITS
     opt
    3.05
     Opt
    2.78
    opt
    2.73
    Opt
    2.59
     opting
    2.19
     opted
    1.98
     opts
    1.93
     OPT
    1.78
    OPT
    1.72
    opted
    1.61
    Activations Density 0.046%

    No Known Activations