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. 14-GEMMASCOPE-RES-16K
    6. 145
    Prev
    Next
    INDEX
    Explanations

    references to econometrics and related statistical concepts in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gle
    -0.38
    ступ
    -0.38
     or
    -0.37
    .
    -0.37
    ParallelGroup
    -0.35
    ,
    -0.35
     to
    -0.35
     –
    -0.35
    push
    -0.35
    now
    -0.35
    POSITIVE LOGITS
     kasarigan
    1.08
     itſelf
    1.05
    Autoritní
    1.01
     pleaſure
    0.98
     pageContext
    0.98
     ExecuteAsync
    0.97
     myſelf
    0.96
     lenker
    0.94
     }}$}
    0.92
    ValueStyle
    0.92
    Activations Density 0.192%

    No Known Activations