© 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. 14-GEMMASCOPE-RES-16K
    6. 8587
    Prev
    Next
    INDEX
    Explanations

    numerical values related to scientific or mathematical notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.58
     ainfi
    -0.53
    laştır
    -0.53
     Chwiliwch
    -0.52
     synag
    -0.52
    SqlParameter
    -0.51
     useAppContext
    -0.50
    SourceChecksum
    -0.50
    majánló
    -0.50
    chieht
    -0.50
    POSITIVE LOGITS
    sequence
    0.38
    VersionUID
    0.38
     virke
    0.37
    stateMutability
    0.36
     dissipated
    0.36
    __':
    0.35
     esternos
    0.35
    舺
    0.35
    obby
    0.34
    static
    0.33
    Activations Density 0.153%

    No Known Activations