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. 2-GEMMASCOPE-RES-16K
    6. 4268
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their corresponding attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    RTEE
    -0.84
     queſta
    -0.83
    uxxxx
    -0.81
    awtextra
    -0.80
    webElementXpaths
    -0.76
    MessageTagHelper
    -0.73
    postsleuth
    -0.72
    webElement
    -0.71
     Normdatei
    -0.71
    AccessorTable
    -0.71
    POSITIVE LOGITS
     "
    0.64
     “
    0.63
    ::_('
    0.55
     „
    0.49
     «
    0.49
    ">
    0.49
    ("
    0.48
    <td>
    0.48
    <em>
    0.47
    「
    0.47
    Activations Density 0.111%

    No Known Activations