© 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. 4893
    Prev
    Next
    INDEX
    Explanations

    terms related to logging and data recording processes

    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
    en
    -0.53
     Carav
    -0.52
    1
    -0.52
    y
    -0.49
     dipole
    -0.49
    <strong>
    -0.49
     provi
    -0.48
     Specially
    -0.48
     Mendez
    -0.47
     hand
    -0.47
    POSITIVE LOGITS
     >=",
    0.96
    DataAnnotations
    0.89
    MethodManager
    0.89
    IBarButtonItem
    0.87
    principalColumn
    0.82
    phorbia
    0.82
    InputBorder
    0.82
    mybatisplus
    0.80
     AttributeSet
    0.80
     AssemblyCulture
    0.80
    Activations Density 0.034%

    No Known Activations