© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9303
    Prev
    Next
    INDEX
    Explanations

    phrases related to lack of authorization or permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.54
    webElementXpaths
    -0.54
    DockStyle
    -0.50
    ództ
    -0.46
    PreferredItem
    -0.46
    balleur
    -0.46
    Kariera
    -0.46
     atualizado
    -0.46
     ✭✭
    -0.45
     prácti
    -0.44
    POSITIVE LOGITS
     vorher
    0.81
     beforehand
    0.77
     предвари
    0.76
    事前に
    0.72
    事前
    0.69
     vooraf
    0.67
     consultation
    0.66
     preceded
    0.64
     pre
    0.61
     Consultation
    0.61
    Activations Density 0.447%

    No Known Activations