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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4404
    Prev
    Next
    INDEX
    Explanations

    identifiers and structured data, especially in the context of databases and coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]:
    -0.73
    Autoritní
    -0.73
    FormTagHelper
    -0.70
    ArrowToggle
    -0.69
    "):
    -0.69
     himo
    -0.69
    ')):
    -0.68
    ':[
    -0.67
    BeginContext
    -0.67
    ferrous
    -0.67
    POSITIVE LOGITS
    apimachinery
    0.56
    الحياه
    0.56
    _
    0.53
    TargetException
    0.45
     MonoBehaviour
    0.44
    CGRectMake
    0.43
    iomanip
    0.41
    En
    0.40
    ToScroll
    0.40
    Sora
    0.39
    Activations Density 0.145%

    No Known Activations