© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10789
    Prev
    Next
    INDEX
    Explanations

    references to authorities and official reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    official entities (authorities, crews, officials)

    np_acts-logits-general · gemini-2.0-flash

    Authorities and researchers report

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.66
     carrés
    -0.57
     enfans
    -0.54
     itſelf
    -0.53
    Xpaths
    -0.52
    mappedBy
    -0.52
     êtres
    -0.52
     Houſe
    -0.50
     nonUne
    -0.50
     couver
    -0.50
    POSITIVE LOGITS
     authorities
    0.47
     ProtoMessage
    0.43
    authorities
    0.42
    Authorities
    0.41
    当局
    0.41
     CreateTagHelper
    0.41
     Authorities
    0.38
     investigators
    0.38
     invokingState
    0.36
     صوتيه
    0.36
    Activations Density 0.652%

    No Known Activations