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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12154
    Prev
    Next
    INDEX
    Explanations

    expressions and syntax related to programming functions and data handling

    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
    parsedMessage
    -0.91
     disambiguazione
    -0.62
    TypeMap
    -0.59
     StatefulWidget
    -0.52
    roslav
    -0.51
    裟
    -0.49
     Selig
    -0.49
    IContainer
    -0.49
     CanadaChoose
    -0.49
     understatement
    -0.48
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.52
    except
    0.52
    !),
    0.52
    !)
    0.48
    twimg
    0.46
    ])
    0.45
    setVerticalGroup
    0.45
    Except
    0.45
     except
    0.45
    windowFixed
    0.45
    Activations Density 0.522%

    No Known Activations