© 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. 25-GEMMASCOPE-RES-16K
    11. 10151
    Prev
    Next
    INDEX
    Explanations

    code related to file manipulation and processing methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weil
    -0.68
    enumi
    -0.63
     مشين
    -0.63
     karena
    -0.61
    because
    -0.61
     porque
    -0.60
    Rujuakan
    -0.58
    Because
    -0.55
    karena
    -0.54
    yet
    -0.54
    POSITIVE LOGITS
     using
    1.14
     asynchronously
    1.03
     recursively
    0.87
    using
    0.85
     используя
    0.84
     given
    0.83
     according
    0.81
     USING
    0.80
     utilizzando
    0.79
     utilizing
    0.78
    Activations Density 0.868%

    No Known Activations