© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 373
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions in the text

    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
    Izvori
    -0.74
    principalTable
    -0.73
     démocr
    -0.73
     CascadeType
    -0.73
     transfieras
    -0.73
    SpringRunner
    -0.71
    TargetException
    -0.70
    AxisAlignment
    -0.70
     GenerationType
    -0.69
    Geplaatst
    -0.67
    POSITIVE LOGITS
      
    0.48
    interopRequire
    0.48
    тербург
    0.47
                                   
    0.46
    the
    0.46
     highly
    0.46
     consultato
    0.45
     and
    0.45
     the
    0.45
    oredCriteria
    0.44
    Activations Density 0.425%

    No Known Activations