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. 17-GEMMASCOPE-RES-16K
    6. 9024
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions that indicate structure in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecer
    -0.40
     tut
    -0.39
    fe
    -0.39
     '').
    -0.38
    utu
    -0.38
    *)
    -0.37
     kon
    -0.36
    arkar
    -0.36
     fed
    -0.35
    بوابة
    -0.35
    POSITIVE LOGITS
     diesmal
    2.41
    这一次
    1.73
    这次
    1.65
    今度は
    1.52
    這次
    1.49
     this
    1.42
    今回は
    1.38
    今回も
    1.27
    this
    1.26
    今度
    1.13
    Activations Density 0.289%

    No Known Activations