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. 4-GEMMASCOPE-RES-16K
    6. 15707
    Prev
    Next
    INDEX
    Explanations

    the word "change" in contexts related to processes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     empre
    -0.57
    akam
    -0.53
     sao
    -0.52
    him
    -0.51
    )))));
    -0.50
    que
    -0.49
    DO
    -0.48
    quia
    -0.48
     mümkün
    -0.48
    ICOL
    -0.48
    POSITIVE LOGITS
    URLException
    0.95
     AssemblyCompany
    0.94
    principalColumn
    0.91
     beginnetje
    0.89
    AnchorTagHelper
    0.83
     snippetHide
    0.83
    Хьажоргаш
    0.81
    CloseOperation
    0.79
    SBATCH
    0.79
    LEncoder
    0.78
    Activations Density 0.372%

    No Known Activations