© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 141
    Prev
    Next
    INDEX
    Explanations

    references to collective experiences or sentiments among groups of people

    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
    ագրություններ
    -0.50
    plona
    -0.49
     onlar
    -0.47
    RegistryLite
    -0.46
    ">//
    -0.43
    __*/
    -0.42
    ronesia
    -0.42
    RenderAtEndOf
    -0.42
    SourceChecksum
    -0.42
     Roskov
    -0.42
    POSITIVE LOGITS
     who
    0.82
     people
    0.69
     хто
    0.61
     Americans
    0.59
     mortals
    0.57
     Christians
    0.56
     among
    0.56
     us
    0.55
     folks
    0.54
     involved
    0.52
    Activations Density 0.342%

    No Known Activations