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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 892
    Prev
    Next
    INDEX
    Explanations

    conditional statements involving actions and their limitations or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Only" followed by a condition or result

    np_acts-logits-general · gemini-2.0-flash

    conditioned on "only"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simplemente
    -0.45
     просто
    -0.44
     einfach
    -0.44
     simply
    -0.43
     ſtill
    -0.40
    simply
    -0.39
     Просто
    -0.39
     Simply
    -0.37
    itinéraire
    -0.37
    seam
    -0.35
    POSITIVE LOGITS
    ंदीखरीदारी
    0.69
     only
    0.61
     ExecuteAsync
    0.57
     Only
    0.56
    Only
    0.55
    IndentedString
    0.51
     noDo
    0.51
    only
    0.51
     лишь
    0.50
     AssemblyCompany
    0.50
    Activations Density 0.320%

    No Known Activations