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. 18-GEMMASCOPE-RES-16K
    6. 1467
    Prev
    Next
    INDEX
    Explanations

    references to specific genes and proteins in scientific contexts

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

    Token "O" followed by a variety of characters

    np_acts-logits-general · gemini-2.0-flash

    words starting with or containing O

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.63
    UnusedPrivate
    -0.55
    addGap
    -0.55
    mbggenerated
    -0.53
    ември
    -0.52
    enance
    -0.51
    bitat
    -0.49
     straight
    -0.49
    getReal
    -0.49
    Géographie
    -0.48
    POSITIVE LOGITS
    Tazama
    0.79
     InputDecoration
    0.77
    ThroughAttribute
    0.73
     Oku
    0.70
     Opa
    0.68
    })();
    
    0.68
     ODS
    0.68
     vapormax
    0.64
     crossorigin
    0.64
     OMR
    0.62
    Activations Density 1.304%

    No Known Activations