© 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. 39-GEMMASCOPE-RES-16K
    6. 3316
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming methods and their implementation details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/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.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writerow
    -0.38
     {}".
    -0.31
    PyObject
    -0.30
    딕
    -0.29
    ValueError
    -0.28
    \_
    -0.28
    ↵↵
    -0.27
     …
    -0.26
     Berg
    -0.26
    mathop
    -0.26
    POSITIVE LOGITS
     Java
    1.30
     java
    1.22
    Java
    1.19
    {@
    1.11
    java
    1.05
     {@
    1.05
     JDK
    0.98
    JDK
    0.98
     JAVA
    0.97
     JVM
    0.95
    Activations Density 0.812%

    No Known Activations