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. 7-GEMMASCOPE-RES-16K
    6. 14586
    Prev
    Next
    INDEX
    Explanations

    references to divine manifestations and symbolic elements associated with a particular deity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idopsis
    -0.65
    OGND
    -0.64
    Clik
    -0.51
    ĩa
    -0.51
     Cæsar
    -0.50
     Wittgenstein
    -0.50
    verture
    -0.49
     klarer
    -0.48
    Segoe
    -0.48
     modernist
    -0.48
    POSITIVE LOGITS
    ⓧ
    0.97
    ValueStyle
    0.67
    حياتها
    0.63
    حياته
    0.63
    CURLOPT
    0.62
     StatelessWidget
    0.60
    VIAF
    0.58
    principalTable
    0.56
    BeforeMethod
    0.55
    MethodImpl
    0.54
    Activations Density 0.240%

    No Known Activations