© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8851
    Prev
    Next
    INDEX
    Explanations

    references to the "rear" or "back" of objects, particularly in relation to visual or structural elements

    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
    ronpa
    -0.49
    róleo
    -0.41
     levels
    -0.40
     singularity
    -0.37
    RTCK
    -0.37
     Levels
    -0.37
    Пример
    -0.36
    agramm
    -0.36
    lasma
    -0.36
    angliski
    -0.36
    POSITIVE LOGITS
     behind
    1.02
    Behind
    0.98
     rear
    0.96
     BEHIND
    0.96
    behind
    0.94
     Behind
    0.94
     BACK
    0.93
     Back
    0.92
    Back
    0.91
     back
    0.91
    Activations Density 0.092%

    No Known Activations