© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 4649
    Prev
    Next
    INDEX
    Explanations

    the use of demonstrative pronouns and their forms in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.65
    }),
    
    -0.63
    )++;
    -0.61
    ГЛА
    -0.61
    '])->
    -0.60
    ).
    
    -0.60
    )"),
    -0.60
     EconPapers
    -0.60
    ']],
    -0.59
    ')],
    -0.59
    POSITIVE LOGITS
     is
    0.76
     isn
    0.74
     guy
    0.71
     ain
    0.69
     thing
    0.67
     stuff
    0.64
     wasn
    0.62
     aint
    0.59
    guy
    0.58
    whole
    0.57
    Activations Density 0.231%

    No Known Activations