Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11197
    Prev
    Next
    INDEX
    Explanations

    keywords related to business transactions and corporate activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.47
     lovingly
    -0.44
    ="@+
    -0.44
    SizeMode
    -0.44
     hobbies
    -0.44
    AISSEE
    -0.43
     كومونز
    -0.43
    nictví
    -0.43
     ModelRenderer
    -0.43
     lifestyles
    -0.42
    POSITIVE LOGITS
     leaked
    0.66
     publicly
    0.65
     procedural
    0.65
     clarification
    0.63
     politically
    0.62
     unilaterally
    0.61
     clarifying
    0.58
     briefed
    0.57
     unilateral
    0.57
     diplomatic
    0.57
    Activations Density 0.851%

    No Known Activations