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. 5-GEMMASCOPE-RES-16K
    6. 11057
    Prev
    Next
    INDEX
    Explanations

    names or terms associated with historical figures and their genealogical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.95
     themſelves
    -0.79
     myſelf
    -0.79
     Efq
    -0.76
     poffible
    -0.75
     iſt
    -0.74
     Eſ
    -0.74
     purpoſe
    -0.71
     Chwiliwch
    -0.71
     raiſ
    -0.71
    POSITIVE LOGITS
     de
    0.89
     von
    0.77
    ؤلاء
    0.76
     van
    0.69
     des
    0.69
     Vander
    0.66
     der
    0.66
     De
    0.64
     Von
    0.64
    Vander
    0.62
    Activations Density 0.213%

    No Known Activations