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. 9-GEMMASCOPE-RES-16K
    6. 7914
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and forms of "to be" indicating states of being or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gyhoeddwyd
    -0.72
    SharedCtor
    -0.65
     samh
    -0.62
    Synonymes
    -0.59
    Whatever
    -0.59
     piaci
    -0.58
     dAtA
    -0.58
    randi
    -0.55
     sonhos
    -0.55
     costi
    -0.55
    POSITIVE LOGITS
     able
    0.79
    \"");
    0.73
     getting
    0.69
    buntu
    0.67
    TagHelper
    0.66
    Меня
    0.64
     Меня
    0.64
    mbggenerated
    0.63
     aware
    0.63
     yourself
    0.63
    Activations Density 0.601%

    No Known Activations