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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-GEMMASCOPE-RES-16K
    6. 1117
    Prev
    Next
    INDEX
    Explanations

    verbs and their associated actions related to support and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.32
     himſelf
    -1.19
     Theſe
    -1.14
     purpoſe
    -1.12
     againſt
    -1.11
     itſelf
    -1.09
    Datuak
    -1.07
    bibfield
    -1.06
     Monfieur
    -1.06
    ſelf
    -1.05
    POSITIVE LOGITS
     plus
    0.47
     everybody
    0.43
    Everybody
    0.42
     так
    0.40
     somebody
    0.40
     really
    0.39
    .
    0.39
     uğ
    0.39
     anybody
    0.38
    </strong>
    0.37
    Activations Density 1.362%

    No Known Activations