© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2488
    Prev
    Next
    INDEX
    Explanations

    instances of the word "emerged" and its variations, indicating the discovery or appearance of concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.69
    InjectAttribute
    -0.44
     intptr
    -0.43
    })));
    -0.40
    windowFixed
    -0.39
     antis
    -0.39
    ❃
    -0.38
     bought
    -0.37
    TypedDataSet
    -0.37
    })).
    -0.36
    POSITIVE LOGITS
     emerged
    1.36
     arose
    1.25
     emerge
    1.23
     emerging
    1.20
     emerges
    1.19
     arisen
    1.17
     arise
    1.13
     arises
    1.10
     evolved
    1.06
    Emerging
    1.02
    Activations Density 0.190%

    No Known Activations