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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 15212
    Prev
    Next
    INDEX
    Explanations

    references to barriers and fences, particularly in the context of fortifications and borders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ActionCreators
    -0.73
    createTextNode
    -0.61
    сылкі
    -0.58
     الدولى
    -0.55
     utafitiHapana
    -0.52
     ką
    -0.52
    AppMethodBeat
    -0.51
     بتاريخ
    -0.49
     Aimee
    -0.48
    readValue
    -0.48
    POSITIVE LOGITS
     fences
    1.72
     fence
    1.69
     barriers
    1.59
     Fence
    1.54
     barrier
    1.47
     fencing
    1.42
    fence
    1.41
     Barriers
    1.34
    Fence
    1.33
     walls
    1.32
    Activations Density 0.336%

    No Known Activations