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. 1-GEMMASCOPE-RES-16K
    6. 5948
    Prev
    Next
    INDEX
    Explanations

    relationships and connections between elements in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InlineData
    -0.77
    igurumi
    -0.62
    HostException
    -0.59
    BeginContext
    -0.58
    gameserver
    -0.57
    sieurs
    -0.57
     WaitForSeconds
    -0.56
    +#+#
    -0.56
    ίων
    -0.55
    httphttps
    -0.55
    POSITIVE LOGITS
    forChild
    0.60
     '\\;'
    0.56
    رشف
    0.56
    دانشنامهٔ
    0.55
    msgSender
    0.55
     minutely
    0.54
    ьаж
    0.54
    LookAnd
    0.52
    Демографія
    0.50
    elemField
    0.50
    Activations Density 0.420%

    No Known Activations