© 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. 16-GEMMASCOPE-RES-16K
    11. 13056
    Prev
    Next
    INDEX
    Explanations

    specific character sequences and structures in technical descriptions, particularly related to systems or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impulse
    -0.45
    IUrlHelper
    -0.45
    LElement
    -0.44
    InjectAttribute
    -0.44
     element
    -0.43
    rib
    -0.41
     فريبيس
    -0.40
    gid
    -0.40
     Tid
    -0.39
     betweenstory
    -0.39
    POSITIVE LOGITS
     jsPsych
    0.63
     CreateTagHelper
    0.61
     ProtoMessage
    0.60
    曖昧さ回避
    0.55
     GoogleFonts
    0.53
    oneofs
    0.52
    LookAnd
    0.50
    ioutil
    0.50
    XmlAccessType
    0.47
    ricians
    0.46
    Activations Density 0.491%

    No Known Activations