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. 22-GEMMASCOPE-RES-16K
    6. 13849
    Prev
    Next
    INDEX
    Explanations

    phrases and references to specific days or periods

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

    "day" and associated activities

    np_acts-logits-general · gemini-2.0-flash

    daytime activities and dreams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.91
    /**
    -0.86
    ]]);
    -0.83
    WriteLiteral
    -0.83
    URLException
    -0.82
    Билгалдахарш
    -0.81
    ⓘ
    -0.79
     pinulongan
    -0.77
     typelib
    -0.76
    amerikanischer
    -0.76
    POSITIVE LOGITS
    dreams
    0.88
    dreaming
    0.82
    dream
    0.80
    days
    0.61
    tona
    0.61
     }^{-
    0.55
     рождения
    0.53
     days
    0.52
     DAYS
    0.52
     afternoon
    0.52
    Activations Density 0.087%

    No Known Activations