© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1774
    Prev
    Next
    INDEX
    Explanations

    instances of the word "also" or similar expressions of inclusion in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.58
    esistenza
    -0.51
    ]();
    -0.51
    "];
    
    -0.49
    ՝
    -0.49
    ]';
    -0.49
    änning
    -0.48
    一亮
    -0.47
    fre
    -0.47
    thodoxy
    -0.45
    POSITIVE LOGITS
    時間も
    0.86
     тоже
    0.84
    にも
    0.84
    も
    0.82
     sekal
    0.81
    たちも
    0.80
     भी
    0.80
     cũng
    0.78
     も
    0.77
    人も
    0.77
    Activations Density 0.181%

    No Known Activations