Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 7648
    Prev
    Next
    INDEX
    Explanations

    terms related to consumer rights and protections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    balls
    -0.39
    JoinTable
    -0.38
    SocketAddress
    -0.34
    ̍t
    -0.34
     uska
    -0.33
    ee
    -0.33
    testify
    -0.32
    LayoutManager
    -0.32
    isSuccessful
    -0.31
    pla
    -0.31
    POSITIVE LOGITS
    Hentet
    0.57
    󠁮
    0.54
     habits
    0.49
    PullParser
    0.47
    🟤
    0.46
     invokingState
    0.45
     endblock
    0.44
    setViewportView
    0.43
    MessageTagHelper
    0.43
     grades
    0.42
    Activations Density 0.295%

    No Known Activations