© 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. 28-GEMMASCOPE-RES-16K
    6. 4435
    Prev
    Next
    INDEX
    Explanations

    instances of imaginative scenarios or hypothetical situations

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

    "imagine" or related words

    np_acts-logits-general · gemini-2.0-flash

    imagine that or DNA hybridization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    üglich
    -0.41
     keduanya
    -0.40
     varandra
    -0.39
     jelas
    -0.37
     göster
    -0.36
     הער
    -0.36
     atlik
    -0.35
    impianto
    -0.35
     belirt
    -0.34
     kesin
    -0.34
    POSITIVE LOGITS
     imagine
    1.05
    Imagine
    1.03
     Imagine
    0.99
    imagine
    0.98
     imagines
    0.81
     IMAG
    0.81
    ंदीखरीदारी
    0.78
     hypothetical
    0.75
     scenarios
    0.72
     imagined
    0.71
    Activations Density 0.250%

    No Known Activations