© 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. 5-GEMMASCOPE-RES-16K
    11. 13659
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "serious" and its variations indicating significant issues or concerns

    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
    LookAnd
    -0.89
    MLLoader
    -0.84
    MigrationBuilder
    -0.83
    ContentAlignment
    -0.79
    fjspx
    -0.78
    NOPQRST
    -0.78
    ⟬
    -0.76
    vismo
    -0.75
    
    -0.71
    canActivate
    -0.71
    POSITIVE LOGITS
     serious
    1.98
     Serious
    1.92
    Serious
    1.87
    serious
    1.81
     seriously
    1.61
     serio
    1.54
     sério
    1.42
     serius
    1.40
     sérieux
    1.36
     seriousness
    1.25
    Activations Density 0.063%

    No Known Activations