© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8992
    Prev
    Next
    INDEX
    Explanations

    terms associated with "semi" in various contexts, focusing heavily on semi-structured or semi-parametric concepts

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

    starting with "semi" or "Semi"

    np_acts-logits-general · gemini-2.0-flash

    prefix semi- followed by parametric

    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
     MotionEvent
    -0.60
     ]}
    -0.57
    SuppressMessage
    -0.57
    databind
    -0.56
    AtIndexPath
    -0.55
    Geografi
    -0.53
     FishBase
    -0.52
    denk
    -0.52
    able
    -0.50
    LayoutInflater
    -0.49
    POSITIVE LOGITS
     semis
    1.03
     SEMI
    0.97
     semi
    0.94
     Semi
    0.94
     Sem
    0.87
     SEM
    0.86
     semic
    0.85
    Semi
    0.83
     sem
    0.82
    Sem
    0.81
    Activations Density 0.093%

    No Known Activations