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. 15-GEMMASCOPE-RES-16K
    6. 4356
    Prev
    Next
    INDEX
    Explanations

    indicators of substantial shifts, changes, or transformations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -1.07
    RenderAtEndOf
    -1.05
    MemoryWarning
    -0.99
     Мексичка
    -0.99
    setVerticalGroup
    -0.99
     tartalomajánló
    -0.97
    OGND
    -0.97
    ]-'
    -0.97
     GenerationType
    -0.97
    +#+#
    -0.94
    POSITIVE LOGITS
    Check
    0.65
     http
    0.65
    http
    0.63
    Click
    0.62
     #
    0.57
    #
    0.57
    e
    0.57
     Check
    0.56
    check
    0.54
     check
    0.53
    Activations Density 0.116%

    No Known Activations