© 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. 0-GEMMASCOPE-RES-16K
    11. 9409
    Prev
    Next
    INDEX
    Explanations

    references to the Restatement of Torts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Treiber
    -0.55
     AssemblyCulture
    -0.51
    StructEnd
    -0.45
     Laub
    -0.44
    corazón
    -0.43
    "}")
    -0.42
    flashdata
    -0.42
    Erreferentziak
    -0.41
     Schreiber
    -0.41
    ujudkan
    -0.40
    POSITIVE LOGITS
     Energ
    0.60
     Rest
    0.60
     REST
    0.59
    Rest
    0.59
     sensation
    0.57
     myſelf
    0.57
     sensations
    0.56
     Spek
    0.56
     ItemStack
    0.55
    Energ
    0.53
    Activations Density 1.605%

    No Known Activations