© 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. 4-GEMMASCOPE-RES-16K
    6. 9695
    Prev
    Next
    INDEX
    Explanations

    the occurrence of numeric values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zegor
    -0.60
    UnsafeEnabled
    -0.58
    LEncoder
    -0.55
    tellungs
    -0.53
     espect
    -0.52
    antMatchers
    -0.51
    
    -0.49
    OLOGIES
    -0.49
    prá
    -0.48
    ēja
    -0.47
    POSITIVE LOGITS
     Roskov
    0.85
     jScrollPane
    0.85
    +#+#
    0.79
    .)}
    0.76
    <>());
    0.76
     sẻ
    0.66
    ].)
    0.66
    ']")
    0.66
    ).}
    0.65
    .).
    0.65
    Activations Density 0.410%

    No Known Activations