© 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. 33-GEMMASCOPE-RES-16K
    6. 8206
    Prev
    Next
    INDEX
    Explanations

    references to music and related creative works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -1.07
     يتيمه
    -1.00
    <unused43>
    -0.99
    <unused76>
    -0.98
    <unused41>
    -0.98
    AddTagHelper
    -0.98
     ProtoMessage
    -0.97
    <unused42>
    -0.97
    ViewFeatures
    -0.97
    <pad>
    -0.97
    POSITIVE LOGITS
     K
    0.60
     D
    0.59
     T
    0.58
     S
    0.56
    K
    0.54
     P
    0.54
     M
    0.54
     B
    0.52
     E
    0.52
    T
    0.51
    Activations Density 2.160%

    No Known Activations