© 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. 25-GEMMASCOPE-RES-16K
    6. 6309
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to the initialization and encoding of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.60
    oredCriteria
    -0.58
    [[
    -0.54
    ]\
    -0.50
    ]")]
    -0.50
    [['
    -0.49
    []
    -0.49
    ApiModelProperty
    -0.48
    }[\
    -0.48
    tiqueta
    -0.48
    POSITIVE LOGITS
     MainAxisSize
    0.59
     become
    0.53
     utafitiHapana
    0.52
     touches
    0.51
    mişti
    0.50
     Become
    0.50
    Will
    0.50
     consultato
    0.49
    клопе
    0.49
    touches
    0.49
    Activations Density 0.188%

    No Known Activations