© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5089
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formatting elements in equations

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

    Mathematical expressions with an overline and underline

    np_acts-logits-general · gemini-2.0-flash

    LaTeX \smash notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GTCX
    -0.57
    gdx
    -0.51
     spar
    -0.46
     canst
    -0.44
     ProtoMessage
    -0.44
    tex
    -0.42
    landers
    -0.41
    ftagPool
    -0.41
     trag
    -0.41
     plat
    -0.41
    POSITIVE LOGITS
     nakalista
    0.92
     AssemblyCulture
    0.75
     ویکی‌پدی
    0.53
    TargetException
    0.50
     ostavi
    0.46
     мәкал
    0.44
    autoreleasepool
    0.44
    EndGlobal
    0.43
     rajut
    0.41
     bezeichneter
    0.41
    Activations Density 2.141%

    No Known Activations