© 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. 18-GEMMASCOPE-RES-16K
    11. 3971
    Prev
    Next
    INDEX
    Explanations

    items and descriptions related to packaging and design details

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

    Objects within a container

    np_acts-logits-general · gemini-2.0-flash

    contained in plastic or a case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.86
    IUrlHelper
    -0.76
     CreateTagHelper
    -0.70
     ostavi
    -0.64
     mapStateToProps
    -0.63
     Vikipedi
    -0.62
    Personendaten
    -0.61
    مصادر
    -0.60
     beginnetje
    -0.60
    хьтан
    -0.59
    POSITIVE LOGITS
     frame
    0.95
     casing
    0.91
     frames
    0.87
     holder
    0.84
     Frame
    0.83
    frame
    0.81
     container
    0.80
     enclosure
    0.78
     case
    0.75
     framed
    0.74
    Activations Density 0.270%

    No Known Activations