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. 16-GEMMASCOPE-RES-16K
    6. 1452
    Prev
    Next
    INDEX
    Explanations

    various forms of complex scientific and technical terminologies related to biological and chemical substances

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

    Versions or alternate forms of something

    np_acts-logits-general · gemini-2.0-flash

    versions and alternatives

    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
    ContentAsync
    -0.76
     autorytatywna
    -0.62
     везе
    -0.59
     ujednoznacz
    -0.59
     /\.(
    -0.59
    Indented
    -0.55
     المعيارى
    -0.54
    })).
    -0.53
     BoxFit
    -0.52
    CPtr
    -0.52
    POSITIVE LOGITS
     version
    1.63
     versions
    1.54
     versión
    1.32
     versão
    1.31
     versione
    1.31
     VERSION
    1.27
     Versions
    1.25
     versiones
    1.20
     Version
    1.19
    version
    1.19
    Activations Density 0.941%

    No Known Activations