© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2564
    Prev
    Next
    INDEX
    Explanations

    the absence of any activating words or phrases in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    年から
    -0.43
     crianças
    -0.43
     Dienste
    -0.42
     future
    -0.42
    avut
    -0.41
     tæ
    -0.41
    amling
    -0.40
     Gesellschaft
    -0.40
    xtext
    -0.40
    neux
    -0.40
    POSITIVE LOGITS
     negotiations
    1.20
     Negotiations
    1.14
    Negoti
    1.12
     negotiators
    1.06
     negotiation
    1.03
     negotiating
    1.01
     negotiator
    0.98
     Negoti
    0.95
     negotiate
    0.92
     Negotiation
    0.92
    Activations Density 0.274%

    No Known Activations