Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 233
    Prev
    Next
    INDEX
    Explanations

    phrases indicating positive experiences or recommendations for visiting or enjoying a location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     numerus
    -0.50
     poda
    -0.48
     advertise
    -0.47
     advertised
    -0.47
     apresent
    -0.46
     signo
    -0.46
     cesse
    -0.46
     patas
    -0.45
     advertising
    -0.45
    /*++
    -0.44
    POSITIVE LOGITS
     esternos
    0.89
    lorette
    0.75
    BufferException
    0.69
     tartalomajánló
    0.68
     cherchés
    0.66
     Exploring
    0.64
     explore
    0.62
     exploring
    0.62
    endphp
    0.61
     staying
    0.58
    Activations Density 0.180%

    No Known Activations