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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13224
    Prev
    Next
    INDEX
    Explanations

    the presence of PHP closing tags and references to remote control concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dry
    -0.70
    apor
    -0.60
    ILayout
    -0.59
     worse
    -0.58
    Personendaten
    -0.56
    saraba
    -0.54
     εφ
    -0.54
    LayoutStyle
    -0.54
    dry
    -0.53
    kamer
    -0.52
    POSITIVE LOGITS
    ?>
    1.05
    ?>
    
    1.01
    ;?>
    0.94
    ');?>
    0.92
    ?>">
    0.90
    ?>"
    0.89
    endphp
    0.88
    \}
    0.83
    remote
    0.82
    }?>
    0.82
    Activations Density 0.068%

    No Known Activations