Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8549
    Prev
    Next
    INDEX
    Explanations

    pointers and their operations in the context of programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.52
     تضيفلها
    -0.47
    اریخ
    -0.46
     <<<<<<<<<<<<<<
    -0.45
    crumb
    -0.45
    wapV
    -0.44
    دانشنامهٔ
    -0.44
     समीक्षाएं
    -0.43
     Erskine
    -0.42
    yntaxException
    -0.42
    POSITIVE LOGITS
    *>(
    0.45
    prepareStatement
    0.43
    >[]
    0.42
    AccessFile
    0.42
     Patil
    0.40
    bitat
    0.39
    Australie
    0.39
    (&$
    0.39
     "
    0.39
    opoulos
    0.38
    Activations Density 0.105%

    No Known Activations