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. 1-GEMMASCOPE-RES-16K
    6. 15033
    Prev
    Next
    INDEX
    Explanations

    specific names and references related to people, places, and scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.79
    principalColumn
    -0.60
     Réponses
    -0.60
     pinulongan
    -0.59
    =>$
    -0.55
    writeValue
    -0.54
    ها
    -0.53
     Initialized
    -0.53
     &___
    -0.53
    antMatchers
    -0.50
    POSITIVE LOGITS
     Fred
    0.72
     FRED
    0.70
    RenderAtEndOf
    0.70
    ArgsConstructor
    0.66
    Fred
    0.66
    pg
    0.66
     pg
    0.65
    Lionel
    0.59
     Lodge
    0.59
     Ethel
    0.58
    Activations Density 2.279%

    No Known Activations