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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 14829
    Prev
    Next
    INDEX
    Explanations

    brackets and their associated structures in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    的
    -2.14
    の
    -2.06
    의
    -1.27
    ها
    -1.10
    的角度
    -0.96
    的她
    -0.96
    のようです
    -0.91
    のサ
    -0.91
    のほうが
    -0.88
    ก็
    -0.87
    POSITIVE LOGITS
    OOO
    0.61
    aaa
    0.44
     Jornada
    0.42
    arakhand
    0.39
    ारी
    0.39
     Egan
    0.39
    edict
    0.38
    hObject
    0.38
    aat
    0.38
    "");
    0.37
    Activations Density 0.502%

    No Known Activations