© 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. 23-GEMMASCOPE-RES-16K
    11. 8635
    Prev
    Next
    INDEX
    Explanations

    issues related to glitches or errors in systems, especially in software or interfaces

    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
    幾乎
    -0.58
    几乎
    -0.57
     praticamente
    -0.56
     prácticamente
    -0.55
    מעט
    -0.55
     rischio
    -0.54
     téměř
    -0.54
     risks
    -0.53
     threats
    -0.52
     pratiquement
    -0.50
    POSITIVE LOGITS
     somehow
    1.03
    rungsseite
    0.89
     sengaja
    0.85
     فريبيس
    0.85
     somewhere
    0.84
     Somehow
    0.83
    TypedDataSet
    0.83
    somewhere
    0.82
     alguma
    0.81
     виправивши
    0.81
    Activations Density 0.549%

    No Known Activations