© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1489
    Prev
    Next
    INDEX
    Explanations

    elements related to procedural and legal frameworks, particularly in the context of defendants and their rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    appearing after a quantity or variable

    np_acts-logits-general · gemini-2.0-flash

    permanent / seasonally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.67
    Jereo
    -0.57
     createSlice
    -0.55
     Infórmanos
    -0.52
     poveznice
    -0.50
     незавершена
    -0.49
    InjectAttribute
    -0.49
    Atsauces
    -0.47
    RegressionTest
    -0.46
     Privacidade
    -0.46
    POSITIVE LOGITS
     Permanent
    0.39
    ]}>
    0.38
    )}>
    0.38
     permanent
    0.35
     ]
    
    0.35
    ]";
    0.35
     "));
    0.34
     */;
    0.34
     seasonally
    0.34
     permanently
    0.33
    Activations Density 1.011%

    No Known Activations