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. 18-GEMMASCOPE-RES-16K
    6. 2124
    Prev
    Next
    INDEX
    Explanations

    Java-related constructs and components used in GUI programming

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

    Variable names or code snippets

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and programming vocabulary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )}}{
    -0.63
    ']
    
    -0.49
    :]:
    -0.49
    ++]=
    -0.47
    }}}{
    -0.47
     instead
    -0.47
    }}],
    -0.47
    eeq
    -0.47
    ']==
    -0.46
    ]=="
    -0.46
    POSITIVE LOGITS
    SequentialGroup
    0.82
     CascadeType
    0.71
     BoxFit
    0.68
    Personendaten
    0.66
    AndEndTag
    0.64
    MethodManager
    0.62
    HasAnnotation
    0.61
     الدولى
    0.60
    ItemBackground
    0.60
     تضيفلها
    0.59
    Activations Density 0.164%

    No Known Activations