Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 1408
    Prev
    Next
    INDEX
    Explanations

    fields or elements in a form that are marked with an asterisk, indicating they are required for completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     محفوظة
    -0.60
     استنادى
    -0.58
    CppCodeGen
    -0.56
    ExtendWith
    -0.52
     dealloc
    -0.51
     WaitForSeconds
    -0.50
     aDecoder
    -0.50
    setVerticalGroup
    -0.49
    WithMany
    -0.49
    RegistryLite
    -0.49
    POSITIVE LOGITS
    NameInMap
    0.89
    LabelTagHelper
    0.65
    rzost
    0.58
     Pflicht
    0.54
    <bos>
    0.52
    kamp
    0.52
     onPostExecute
    0.50
    jeti
    0.49
     Campos
    0.49
     Validators
    0.49
    Activations Density 0.144%

    No Known Activations