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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10661
    Prev
    Next
    INDEX
    Explanations

    elements related to sizing and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.65
    FormTagHelper
    -0.61
    }\]
    -0.55
    ">',
    -0.50
     nemlig
    -0.49
     Meksiku
    -0.49
    Diweddarwch
    -0.48
     }}-
    -0.48
     resourceCulture
    -0.48
    __',
    -0.47
    POSITIVE LOGITS
    /
    2.25
     /
    1.59
    /
    1.37
    /$
    1.30
    /(
    1.27
    /"
    1.26
    '/
    1.26
    /{
    1.25
     $/
    1.24
    /'
    1.21
    Activations Density 0.391%

    No Known Activations