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. 10-GEMMASCOPE-RES-16K
    6. 4603
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and entities involved in court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.82
    onOptions
    -0.72
     يتيمه
    -0.71
     themſelves
    -0.69
    migrationBuilder
    -0.67
    GEBURTSDATUM
    -0.64
    PyExc
    -0.62
    typeorm
    -0.61
     mergeFrom
    -0.61
    KommentareTeilen
    -0.60
    POSITIVE LOGITS
    titleMargin
    0.45
    glBindTexture
    0.41
    rawtypes
    0.40
     vận
    0.40
    TargetException
    0.40
    一下
    0.38
    略歴
    0.38
     gezet
    0.38
    glBegin
    0.37
     MR
    0.37
    Activations Density 0.642%

    No Known Activations