© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8849
    Prev
    Next
    INDEX
    Explanations

    snippets of code or configuration files related to a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.87
    #+#
    -0.86
    WriteTagHelper
    -0.83
    tvguidetime
    -0.78
    XmlAccessorType
    -0.77
     дописавши
    -0.77
     resourceCulture
    -0.76
    PyExc
    -0.70
    })`
    -0.70
    :+:
    -0.69
    POSITIVE LOGITS
    tector
    0.48
    রণ
    0.45
    signe
    0.44
    ksesta
    0.43
     CPE
    0.43
    4
    0.43
    6
    0.43
    signer
    0.42
    9
    0.42
    7
    0.42
    Activations Density 0.709%

    No Known Activations