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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4979
    Prev
    Next
    INDEX
    Explanations

    technical terms related to hardware specifications and connectivity in electronic devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
     يتيمه
    -0.66
    crat
    -0.49
    ardy
    -0.49
    かた
    -0.45
    cura
    -0.44
     administrative
    -0.44
     Administration
    -0.43
    وسط
    -0.43
     صوتيه
    -0.43
    География
    -0.43
    POSITIVE LOGITS
     canali
    0.68
     незавершена
    0.67
    AnchorStyles
    0.66
    extAlignment
    0.66
    UNUSED
    0.63
    følgelig
    0.62
     ProtoMessage
    0.62
    ]")]
    0.62
    inout
    0.62
     outputs
    0.60
    Activations Density 1.047%

    No Known Activations