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. 21-GEMMASCOPE-RES-16K
    6. 8359
    Prev
    Next
    INDEX
    Explanations

    personal reflections and decisions regarding choices or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.81
    RectangleBorder
    -0.77
    andExpect
    -0.65
     informée
    -0.64
     milliers
    -0.61
    demic
    -0.60
    ::$_
    -0.58
     Endlich
    -0.57
     mergeFrom
    -0.55
    chafft
    -0.55
    POSITIVE LOGITS
     opted
    1.14
     opting
    1.07
     opt
    1.02
     prefer
    0.91
     optar
    0.89
     preferring
    0.88
     chose
    0.87
     sticking
    0.84
     opts
    0.84
     choose
    0.80
    Activations Density 0.520%

    No Known Activations