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. 6-GEMMASCOPE-RES-16K
    6. 13455
    Prev
    Next
    INDEX
    Explanations

    Java method definitions and event handling functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     berp
    -0.53
    듭
    -0.50
     mudah
    -0.49
     dilan
    -0.48
    NameLabel
    -0.47
    naphthal
    -0.47
    ngth
    -0.47
    rrggbb
    -0.47
    mudah
    -0.46
     صوتيه
    -0.46
    POSITIVE LOGITS
    FXML
    1.55
     actionPerformed
    1.05
    RunAsync
    0.94
    beforeEach
    0.89
    DoubleQuotes
    0.88
    bukkit
    0.86
    gdx
    0.85
    ])):
    0.84
    AndEndTag
    0.84
    GEBURTSDATUM
    0.81
    Activations Density 0.009%

    No Known Activations