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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15539
    Prev
    Next
    INDEX
    Explanations

    instances of the word "make" and its variations, indicating a focus on creation or production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pulumi
    -0.50
    optarg
    -0.48
    webElementXpaths
    -0.44
     torchvision
    -0.43
     kasarigan
    -0.42
    ordinateur
    -0.41
    Abbildung
    -0.41
    currentNode
    -0.40
    Witam
    -0.40
     pimienta
    -0.40
    POSITIVE LOGITS
    make
    1.07
     make
    0.97
     Make
    0.96
    Make
    0.95
    makes
    0.94
    made
    0.93
    Making
    0.91
    making
    0.91
    MAKE
    0.90
     MAKE
    0.89
    Activations Density 0.154%

    No Known Activations