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. 22-GEMMASCOPE-RES-16K
    6. 11141
    Prev
    Next
    INDEX
    Explanations

    references to specific biblical passages and scripture citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Bible verses with chapter and verse notation

    np_acts-logits-general · gemini-2.0-flash

    bible verses and scripture references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }$​
    -0.54
    cett
    -0.51
    }]
    
    -0.48
    larım
    -0.47
    oznam
    -0.47
     rechange
    -0.46
    strup
    -0.46
    omia
    -0.46
    gesteld
    -0.46
     hoạch
    -0.46
    POSITIVE LOGITS
    +#+#
    0.79
     MainAxisSize
    0.72
    ReusableCell
    0.71
     BitmapFactory
    0.68
    @[+][
    0.68
     BoxFit
    0.66
     HasFactory
    0.65
     متعلقه
    0.62
     kaynağından
    0.62
     JpaRepository
    0.60
    Activations Density 0.266%

    No Known Activations