© 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. 0-GEMMASCOPE-RES-16K
    6. 7850
    Prev
    Next
    INDEX
    Explanations

    mentions of funding organizations and their roles in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.77
     Shakspeare
    -1.58
     Monfieur
    -1.55
     myſelf
    -1.51
     doubtnut
    -1.47
    Obrázky
    -1.47
     purpoſe
    -1.38
     Anſ
    -1.36
     Jefus
    -1.36
     Reſ
    -1.35
    POSITIVE LOGITS
     
    1.05
    <eos>
    1.03
     The
    0.90
     in
    0.88
     and
    0.85
     I
    0.84
     “
    0.80
    ,
    0.77
    ↵
    0.77
     "
    0.76
    Activations Density 0.700%

    No Known Activations