Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 12429
    Prev
    Next
    INDEX
    Explanations

    the word "so" and its variations, indicating emphasis or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.62
     defaultstate
    -0.61
    XmlRootElement
    -0.59
    />";
    -0.58
     DBNull
    -0.53
    audiovisuel
    -0.53
     Else
    -0.52
    metheus
    -0.52
    BeginContext
    -0.52
     "..\..\
    -0.51
    POSITIVE LOGITS
     far
    3.16
    far
    2.32
    Far
    1.86
     Far
    1.84
     FAR
    1.67
     langt
    1.55
     jauh
    1.49
    FAR
    1.47
     lejos
    1.26
     далеко
    1.24
    Activations Density 0.145%

    No Known Activations