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. 2-GEMMASCOPE-RES-16K
    6. 15130
    Prev
    Next
    INDEX
    Explanations

    terms related to nodes and networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.68
     MainAxisSize
    -0.62
    ('',
    -0.61
    ifah
    -0.53
     localVar
    -0.53
    tonsoft
    -0.52
    > 
    -0.52
    sharp
    -0.52
    △
    -0.51
    ốp
    -0.51
    POSITIVE LOGITS
     nodes
    1.50
     Nodes
    1.28
    nodes
    1.22
    Nodes
    1.12
     portals
    0.89
     portal
    0.84
    NODES
    0.75
    节点
    0.74
     Portal
    0.73
    Portal
    0.71
    Activations Density 0.108%

    No Known Activations