Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13249
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and constructs within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    createObject
    -0.30
    <eos>
    -0.28
     adop
    -0.24
    })+
    -0.23
    stylers
    -0.23
    ↵
    -0.23
    <bos>
    -0.23
    },
    
    -0.23
     اص
    -0.23
     hal
    -0.23
    POSITIVE LOGITS
     kasarigan
    1.00
    RegressionTest
    0.86
    ########.
    0.82
     שוליים
    0.75
    WebServlet
    0.72
     Anſ
    0.71
    jsxFileName
    0.69
    Билгалдахарш
    0.69
     nakalista
    0.67
     zza
    0.66
    Activations Density 0.306%

    No Known Activations