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. 6-GEMMASCOPE-RES-16K
    6. 6086
    Prev
    Next
    INDEX
    Explanations

    instances of decision-making and evaluation in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.93
    RTLD
    -0.80
     Reſ
    -0.76
     ―――――
    -0.73
     poffible
    -0.71
     EClass
    -0.70
    ſelf
    -0.69
     ſtate
    -0.69
     Diſ
    -0.67
    ſelves
    -0.67
    POSITIVE LOGITS
    IntoConstraints
    0.57
     pretty
    0.50
     only
    0.47
     acordo
    0.47
    weist
    0.46
     it
    0.46
    ying
    0.45
    <bos>
    0.45
     immediately
    0.45
     keinem
    0.44
    Activations Density 0.322%

    No Known Activations