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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 6035
    Prev
    Next
    INDEX
    Explanations

    the word "also" and its associated contexts in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -1.69
    also
    -1.46
    Also
    -1.25
     também
    -1.22
     Also
    -1.19
     également
    -1.14
     anche
    -1.13
     также
    -1.12
     también
    -1.11
     również
    -1.10
    POSITIVE LOGITS
     known
    0.72
    तर
    0.72
     includes
    0.70
    षण
    0.69
     noteworthy
    0.69
    adpleegd
    0.68
     happens
    0.67
     included
    0.67
    parsedMessage
    0.66
     וגם
    0.63
    Activations Density 0.244%

    No Known Activations