© 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. 9966
    Prev
    Next
    INDEX
    Explanations

    instances of the suffix "-able"

    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
     surla
    -0.60
    __*/
    -0.57
    ]='\
    -0.52
     raiſ
    -0.48
     HttpHeaders
    -0.48
     userID
    -0.47
    Transkript
    -0.47
     ſch
    -0.47
     *++
    -0.47
     ſta
    -0.47
    POSITIVE LOGITS
    UE
    0.63
     Woods
    0.59
    ue
    0.59
     woods
    0.58
    ificantly
    0.50
     lift
    0.49
    mm
    0.49
     brim
    0.49
     ddelweddau
    0.48
     masked
    0.48
    Activations Density 0.284%

    No Known Activations