© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3013
    Prev
    Next
    INDEX
    Explanations

    structures and definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     „
    -0.64
     «
    -0.59
    AnchorStyles
    -0.54
    Portail
    -0.49
    axle
    -0.48
     Ashby
    -0.47
     (;
    -0.46
     Lipp
    -0.46
    \\
    -0.46
     ox
    -0.46
    POSITIVE LOGITS
    IUrlHelper
    0.72
     resourceCulture
    0.70
     verrez
    0.68
     numberWith
    0.67
     JpaRepository
    0.67
     ThemeData
    0.67
    ByExample
    0.66
     Altri
    0.66
     Egli
    0.66
    Dış
    0.66
    Activations Density 0.141%

    No Known Activations