© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9255
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and functions, particularly those related to input/output operations and network socket programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.73
    <eos>
    -0.45
    ↵
    -0.41
     +
    -0.38
    </em>
    -0.38
    }\
    -0.36
    </strong>
    -0.35
    *}
    -0.34
    }`).
    -0.33
    }+
    -0.33
    POSITIVE LOGITS
     MainAxisSize
    0.93
    ChildScrollView
    0.87
    SourceChecksum
    0.86
    Personendaten
    0.86
    MigrationBuilder
    0.84
     defaultstate
    0.83
     '\\;'
    0.83
    WebElementEntity
    0.82
     AssemblyVersion
    0.82
     autorytatywna
    0.81
    Activations Density 2.702%

    No Known Activations