© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 8328
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the addition or enhancement of qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :].
    -0.57
    ArrowToggle
    -0.56
    aarrggbb
    -0.56
    offsetof
    -0.54
     doInBackground
    -0.54
    }],
    -0.52
    asInstanceOf
    -0.52
     partielle
    -0.51
     að
    -0.51
     Schlegel
    -0.50
    POSITIVE LOGITS
     depth
    0.95
     personality
    0.89
     charm
    0.87
     piz
    0.87
     character
    0.81
     flair
    0.79
     oom
    0.77
     drama
    0.77
     dimension
    0.75
     interest
    0.75
    Activations Density 0.243%

    No Known Activations