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. 15-GEMMASCOPE-RES-16K
    6. 2299
    Prev
    Next
    INDEX
    Explanations

    references to organizations, publications, or formal groups related to journalism and their impact on industry standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بيها
    -0.67
    </tfoot>
    -0.62
    EndGlobal
    -0.61
    Rhestr
    -0.59
     FetchType
    -0.59
    autique
    -0.58
    ReusableCell
    -0.57
    principalColumn
    -0.57
    --}}
    -0.57
    '},
    
    -0.57
    POSITIVE LOGITS
     "...
    1.45
     “…
    1.45
     "[
    1.42
     “[
    1.42
     “...
    1.35
     "
    1.30
     “
    1.22
    “[
    1.21
    “…
    1.19
    "[
    1.10
    Activations Density 0.826%

    No Known Activations