© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3553
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to dreams and aspirations

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

    "dream" or "dreaming"

    np_acts-logits-general · gemini-2.0-flash

    dream

    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
    AddWithValue
    -0.71
    Personendaten
    -0.67
    HttpClientModule
    -0.62
    AndEndTag
    -0.59
     SqlParameter
    -0.58
    pgsql
    -0.57
    spp
    -0.53
    }))
    
    -0.53
    autoconfigure
    -0.53
    PCell
    -0.53
    POSITIVE LOGITS
     Dream
    1.18
     DREAM
    1.17
     dream
    1.15
     dreams
    1.12
    Dream
    1.07
     Dreams
    1.04
    DREAM
    1.03
    dream
    1.01
    Dreams
    1.01
     Dreaming
    0.99
    Activations Density 0.079%

    No Known Activations