© 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-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1521
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and syntactical elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
     habet
    -0.46
     επί
    -0.45
    RetentionPolicy
    -0.44
    ĝo
    -0.43
     uuidv
    -0.41
    ])));
    -0.41
    EnableWeb
    -0.40
     quidem
    -0.39
     vPvB
    -0.38
    AutoScaleMode
    -0.38
    POSITIVE LOGITS
    MathML
    4.31
    semantics
    0.65
     Audiodateien
    0.61
    URLException
    0.60
    math
    0.60
    MemoryWarning
    0.59
    mtable
    0.59
     الحره
    0.58
    Werdegang
    0.58
     Obrador
    0.57
    Activations Density 0.047%

    No Known Activations