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. 10-GEMMASCOPE-RES-16K
    6. 10774
    Prev
    Next
    INDEX
    Explanations

    specific numerical values related to vehicle specifications or recall information

    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
    MENAFN
    -0.78
    forChild
    -0.63
    //
    -0.63
    ThroughAttribute
    -0.62
    Hrsg
    -0.61
    IonicModule
    -0.59
     المعيارى
    -0.58
    peth
    -0.58
    LookAnd
    -0.58
    utuhkan
    -0.58
    POSITIVE LOGITS
     compagn
    0.52
     rear
    0.49
     InputDecoration
    0.48
     rocz
    0.48
    لينكات
    0.46
     sportivo
    0.46
     year
    0.44
    सन्दर्भ
    0.44
     culoare
    0.44
     sorteo
    0.43
    Activations Density 0.182%

    No Known Activations