© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9616
    Prev
    Next
    INDEX
    Explanations

    the present tense of verbs

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

    the contraction "it's" (it is).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.73
    CDCl
    -0.64
    GOTREF
    -0.62
     CreateTagHelper
    -0.61
     lenker
    -0.61
    msgTypes
    -0.59
    ReusableCell
    -0.58
     дописавши
    -0.57
    Бахар
    -0.57
     uLocal
    -0.57
    POSITIVE LOGITS
     been
    0.84
     not
    0.77
     gonna
    0.66
     got
    0.64
     gotta
    0.56
     always
    0.54
     actually
    0.52
     also
    0.52
     probably
    0.50
     supposed
    0.50
    Activations Density 0.153%

    No Known Activations