© 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. 372
    Prev
    Next
    INDEX
    Explanations

    names, titles, and terms that indicate identification or classification

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

    alternate names

    np_acts-logits-general · gemini-2.0-flash

    alternative names

    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
    WithIOException
    -0.72
    RenderAtEndOf
    -0.66
     старости
    -0.60
    yntaxException
    -0.58
     gynhyrchwyd
    -0.58
    lioz
    -0.58
     سكانية
    -0.56
     Chwiliwch
    -0.56
    SharedCtor
    -0.56
     tartalomajánló
    -0.54
    POSITIVE LOGITS
     aka
    1.62
     popularly
    1.54
    aka
    1.47
     known
    1.44
     AKA
    1.43
     nicknamed
    1.39
    commonly
    1.36
    known
    1.36
     commonly
    1.36
    AKA
    1.35
    Activations Density 0.370%

    No Known Activations