© 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 EvalsExportsAPI 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. 13034
    Prev
    Next
    INDEX
    Explanations

    elements and parameters related to data structures and programming logic

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

    Code or special characters

    np_acts-logits-general · gemini-2.0-flash

    mtu, flex, deterioration

    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
     فريبيس
    -0.96
     â
    -0.90
    AndEndTag
    -0.78
     fieldNum
    -0.76
     AttributeSet
    -0.74
     …
    -0.72
     propOrder
    -0.71
    WebVitals
    -0.71
    ftagPool
    -0.70
    UrlResolution
    -0.70
    POSITIVE LOGITS
    ...
    0.78
    Життєпис
    0.69
    --
    0.69
    ....
    0.65
    ...@
    0.62
    —
    0.58
    .--
    0.57
    .​
    0.56
    שְׁ
    0.55
    </b>
    0.55
    Activations Density 2.534%

    No Known Activations