© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8467
    Prev
    Next
    INDEX
    Explanations

    references to biblical scripture and specific passages

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

    Biblical verses or references

    np_acts-logits-general · gemini-2.0-flash

    bind on earth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useDispatch
    -0.53
    iket
    -0.49
     *);
    -0.46
     amount
    -0.42
     rate
    -0.42
    less
    -0.42
    gesteld
    -0.40
    entista
    -0.39
    กัน
    -0.39
    ային
    -0.39
    POSITIVE LOGITS
     MainAxisSize
    0.91
     InputDecoration
    0.79
     BitmapFactory
    0.79
    abetes
    0.76
    +#+#
    0.76
     passim
    0.75
     HasFactory
    0.74
    iastes
    0.71
     BoxFit
    0.70
     chapters
    0.70
    Activations Density 0.073%

    No Known Activations