© 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. 2-GEMMASCOPE-RES-16K
    6. 12653
    Prev
    Next
    INDEX
    Explanations

    references to time indicators, specifically formatted times such as "AM" and "PM"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAlignment
    -0.60
     okuyayım
    -0.48
    ouille
    -0.46
     Reputation
    -0.46
     repertoire
    -0.46
     reputation
    -0.45
    rativa
    -0.45
     isComment
    -0.45
     weevil
    -0.45
     MOUSE
    -0.44
    POSITIVE LOGITS
     AM
    1.13
     PM
    0.71
    AM
    0.67
    到
    0.52
    PM
    0.51
    Amanda
    0.44
     Amanda
    0.41
    baomidou
    0.40
    AMB
    0.38
     amanda
    0.38
    Activations Density 0.056%

    No Known Activations