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. 3-GEMMASCOPE-RES-16K
    6. 12329
    Prev
    Next
    INDEX
    Explanations

    terms related to composition and structuring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.47
    提到
    -0.45
    Voodoo
    -0.44
    testcase
    -0.43
    ęć
    -0.42
     KeyCode
    -0.40
    Appropriate
    -0.40
     Hines
    -0.40
    gın
    -0.40
    Trivia
    -0.40
    POSITIVE LOGITS
     composing
    1.46
     compose
    1.39
    composed
    1.36
     compos
    1.32
     composition
    1.32
     Composition
    1.31
     compone
    1.26
     compositions
    1.25
     composed
    1.24
    Composition
    1.24
    Activations Density 0.286%

    No Known Activations