© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3651
    Prev
    Next
    INDEX
    Explanations

    code-related keywords or functions

    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
     '\\;'
    -1.05
    basicConfig
    -0.96
     Мексичка
    -0.88
    WriteTagHelper
    -0.87
    IntoConstraints
    -0.86
    CppMethod
    -0.85
    IBarButtonItem
    -0.81
    CppCodeGen
    -0.81
    PathVariable
    -0.80
    AddTagHelper
    -0.80
    POSITIVE LOGITS
     an
    0.47
     general
    0.47
     fact
    0.42
    </strong>
    0.41
     damage
    0.40
     ringan
    0.40
     light
    0.39
     not
    0.39
     look
    0.39
    createView
    0.39
    Activations Density 0.024%

    No Known Activations