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. 25-GEMMASCOPE-RES-16K
    6. 4424
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to technical specifications and evaluations

    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
     softness
    -0.95
     Simplicity
    -0.90
     simplicity
    -0.88
    Simplicity
    -0.88
     purity
    -0.87
    correctly
    -0.85
    chability
    -0.84
     neutrality
    -0.82
     Safely
    -0.82
     Priv
    -0.82
    POSITIVE LOGITS
     influential
    0.74
     faithful
    0.72
     respectful
    0.72
     profitable
    0.71
     reliable
    0.71
     confident
    0.70
     beneficial
    0.70
     valuable
    0.69
     tolerant
    0.69
     accurate
    0.69
    Activations Density 0.478%

    No Known Activations