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. 7697
    Prev
    Next
    INDEX
    Explanations

    references to siblings and familial relationships

    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
    })));
    -0.85
     CLR
    -0.79
    isticated
    -0.78
    enment
    -0.72
    "]}
    -0.72
     ECS
    -0.71
     Gandalf
    -0.70
     Gant
    -0.70
     relu
    -0.69
     dci
    -0.68
    POSITIVE LOGITS
     BROTHER
    1.58
     brother
    1.52
     brothers
    1.50
    brother
    1.48
    Brother
    1.40
     Brother
    1.40
     sister
    1.36
    brothers
    1.30
     Brothers
    1.28
     Sister
    1.24
    Activations Density 0.050%

    No Known Activations