© 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. 5-GEMMASCOPE-RES-16K
    11. 14972
    Prev
    Next
    INDEX
    Explanations

    headings or markers indicating sections of a formal document, such as research papers or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كمان
    -0.58
    VersionUID
    -0.56
    ParallelGroup
    -0.53
     assumptions
    -0.47
     Eastwood
    -0.47
     Monmouth
    -0.46
     needles
    -0.45
     كومونز
    -0.45
     Nottingham
    -0.44
     سكان
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.78
     ujednoznacz
    0.74
     يتيمه
    0.72
    KURZBESCHREIBUNG
    0.67
    UpInside
    0.64
    Tikang
    0.63
    expandindo
    0.60
    一座
    0.60
    uxxxx
    0.60
    miny
    0.59
    Activations Density 0.006%

    No Known Activations