© 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. 40-GEMMASCOPE-RES-16K
    6. 1378
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming syntax elements, particularly those related to functions and matrix operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.56
    fjspx
    -0.52
     continúas
    -0.49
     (?)
    -0.46
    UserScript
    -0.45
    -------
    -0.44
     gynhyrchwyd
    -0.42
    GEBURTSDATUM
    -0.42
    (?)
    -0.42
    ものの
    -0.42
    POSITIVE LOGITS
    」「
    0.54
    XmlAccessType
    0.50
    』『
    0.49
     AssemblyCompany
    0.49
    ”“
    0.45
    `,`
    0.44
     、
    0.42
     houſe
    0.42
     Roskov
    0.41
    》《
    0.41
    Activations Density 1.897%

    No Known Activations