© 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. 4-GEMMASCOPE-RES-16K
    11. 1044
    Prev
    Next
    INDEX
    Explanations

    terms related to legal agreements and policies

    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
     typelib
    -0.97
     ModelExpression
    -0.84
    InputBorder
    -0.83
     препратки
    -0.69
    makeConstraints
    -0.68
    IUrlHelper
    -0.68
    dataclass
    -0.68
     INTERESAR
    -0.67
    HtmlAttribute
    -0.67
     nakalista
    -0.67
    POSITIVE LOGITS
     herein
    0.65
     hereby
    0.51
    rawDesc
    0.48
     comigo
    0.47
     venons
    0.47
     bàn
    0.42
     hereof
    0.42
     herewith
    0.41
     présentes
    0.40
    假
    0.40
    Activations Density 0.856%

    No Known Activations