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. 16-GEMMASCOPE-RES-16K
    6. 8909
    Prev
    Next
    INDEX
    Explanations

    references to political parties and their associated actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Leaving, defecting, or resigning from a group

    np_acts-logits-general · gemini-2.0-flash

    joining or quitting parties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     focus
    -0.49
    uidado
    -0.47
    솜
    -0.46
     manages
    -0.43
    ckså
    -0.43
    >[]
    -0.42
    rouwen
    -0.42
     special
    -0.42
     strict
    -0.41
     task
    -0.41
    POSITIVE LOGITS
    AddTagHelper
    0.93
     joining
    0.91
     switch
    0.90
    LookAnd
    0.89
     Joined
    0.88
     Joining
    0.87
     opting
    0.87
     quitting
    0.87
     Switching
    0.83
     quitted
    0.83
    Activations Density 0.457%

    No Known Activations