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. 23-GEMMASCOPE-RES-16K
    6. 5654
    Prev
    Next
    INDEX
    Explanations

    specific political figures and their roles in elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yoruba
    -0.55
     referrerpolicy
    -0.54
    providedIn
    -0.54
    WriteTagHelper
    -0.52
    MockBean
    -0.51
    ้ว
    -0.50
     Ogun
    -0.50
     Khmer
    -0.50
    Siz
    -0.49
     Chennai
    -0.49
    POSITIVE LOGITS
     Normdatei
    0.63
     démocr
    0.49
    aturen
    0.49
    󠁴
    0.48
     Adam
    0.48
     Ciro
    0.48
    addCriterion
    0.47
     Gala
    0.46
     ADAM
    0.46
     préc
    0.46
    Activations Density 0.077%

    No Known Activations