© 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. 2-GEMMASCOPE-RES-16K
    11. 16152
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dream" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.90
    帖最后由
    -0.73
     ABV
    -0.67
    Personendaten
    -0.65
    ิลปะ
    -0.63
    ppery
    -0.63
    inent
    -0.63
     derer
    -0.60
     paroisse
    -0.60
    Shots
    -0.59
    POSITIVE LOGITS
     dream
    3.89
     Dream
    3.52
    dream
    3.38
     DREAM
    3.36
     dreams
    3.33
    Dream
    3.33
    DREAM
    2.94
     dreamed
    2.85
     dreaming
    2.80
     Dreams
    2.79
    Activations Density 0.039%

    No Known Activations