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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6666
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific character or symbol, particularly the letter 'x'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.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
    })()
    -0.40
     spre
    -0.40
    gesch
    -0.39
     poème
    -0.37
    娘
    -0.36
    Aholisi
    -0.36
     Tourisme
    -0.35
     бюдже
    -0.35
    bast
    -0.35
     pote
    -0.35
    POSITIVE LOGITS
    GraphicsUnit
    6.16
    ValueStyle
    0.94
    AnchorStyles
    0.88
    DoubleQuotes
    0.86
     AssemblyCompany
    0.85
     AttributeSet
    0.85
     MessageBoxIcon
    0.83
    AutoScaleMode
    0.77
    ISupport
    0.74
    WireFormat
    0.72
    Activations Density 0.001%

    No Known Activations