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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 15324
    Prev
    Next
    INDEX
    Explanations

    concepts and expressions related to fear and anxiety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.75
     nahilalakip
    -0.74
    WriteTagHelper
    -0.70
     McKe
    -0.69
     EconPapers
    -0.67
     Ashton
    -0.64
     متحده
    -0.63
    లాలు
    -0.62
    `}
    -0.62
    protoimpl
    -0.61
    POSITIVE LOGITS
     Fear
    1.65
     FEAR
    1.62
     fear
    1.58
     fears
    1.58
     Fears
    1.49
    fear
    1.49
    Fear
    1.47
     feared
    1.29
    fraid
    1.21
     fearful
    1.19
    Activations Density 0.079%

    No Known Activations