© 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. 21-GEMMASCOPE-RES-16K
    6. 15370
    Prev
    Next
    INDEX
    Explanations

    technical specifications and parameters related to object properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GeoNames
    -0.67
     betweenstory
    -0.67
    UnitTesting
    -0.66
    mybatisplus
    -0.62
    noid
    -0.60
     مصرى
    -0.59
    thenReturn
    -0.58
    HostException
    -0.58
     שוליים
    -0.58
     popoli
    -0.58
    POSITIVE LOGITS
    styleType
    0.94
    ":{
    0.64
    isContained
    0.57
    adaptiveStyles
    0.57
    $")
    0.54
    ]}"
    0.54
    awtextra
    0.54
    */)
    0.53
    }")]
    0.53
    chesse
    0.53
    Activations Density 0.058%

    No Known Activations