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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12527
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to queueing and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     terrorism
    -0.68
    strides
    -0.63
    ngOnInit
    -0.63
    terror
    -0.63
     terrorist
    -0.63
     المثال
    -0.60
     inoxidable
    -0.58
     terrorists
    -0.57
     Hildebrand
    -0.57
     aventures
    -0.56
    POSITIVE LOGITS
     queue
    2.56
    queue
    2.41
     Queue
    2.27
    Queue
    2.23
     queues
    2.12
    QUEUE
    1.94
    queues
    1.71
     queuing
    1.58
    Queues
    1.56
     queued
    1.46
    Activations Density 0.062%

    No Known Activations