© 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. 15-GEMMASCOPE-RES-16K
    11. 12447
    Prev
    Next
    INDEX
    Explanations

    the opening of a document or section

    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
    WarningLevel
    -0.60
    uche
    -0.58
    不高
    -0.57
    WriteBarrier
    -0.54
    @[+][
    -0.53
    IRECT
    -0.52
    ocats
    -0.52
    }),
    -0.51
    旺
    -0.51
     createContext
    -0.50
    POSITIVE LOGITS
    تقاوى
    0.64
     ſche
    0.62
    bezpe
    0.58
     poffe
    0.58
     ExecuteAsync
    0.57
     preſent
    0.57
     ſtate
    0.56
    JspWriter
    0.55
     médicaux
    0.55
     AssemblyCulture
    0.53
    Activations Density 0.239%

    No Known Activations