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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3202
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and punctuation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing parentheses followed by numbers or numeric field identifiers in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.52
     мәкал
    -0.45
    HasForeignKey
    -0.45
    Portale
    -0.44
    principalColumn
    -0.43
     esboço
    -0.42
    afficheront
    -0.41
     Stiff
    -0.41
    Бележки
    -0.40
     елның
    -0.39
    POSITIVE LOGITS
    saraba
    0.57
    ']))
    0.57
    __))
    0.54
    "]))
    0.53
    '))
    0.51
    '])
    0.48
     perlahan
    0.48
    Personendaten
    0.47
    >)
    0.47
    ''')
    0.47
    Activations Density 1.186%

    No Known Activations