© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9554
    Prev
    Next
    INDEX
    Explanations

    elements related to recruitment and training processes in various contexts, particularly indicating organization and structure

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

    training or being trained

    np_acts-logits-general · gemini-2.0-flash

    training and being trained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Drapeau
    -0.57
     Վերցված
    -0.57
    endphp
    -0.54
    '][$
    -0.48
    PointerException
    -0.43
    ="'.$
    -0.43
    */;
    -0.43
    StatusLabel
    -0.42
     zucchero
    -0.42
    tható
    -0.41
    POSITIVE LOGITS
     training
    2.69
     Training
    2.40
    Training
    2.39
    training
    2.34
     TRAINING
    2.27
     trained
    2.01
    TRAINING
    2.00
     trainings
    1.93
     Trainings
    1.79
     Trained
    1.76
    Activations Density 0.235%

    No Known Activations