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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53200
    Prev
    Next
    INDEX
    Explanations

    indicators of financial responsibility and caution in communications

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

    no competing interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -1.63
    تقاوى
    -1.45
     виправивши
    -1.41
    expandindo
    -1.37
     صوتيه
    -1.36
     متعلقه
    -1.35
     CreateTagHelper
    -1.34
     Roskov
    -1.30
    Personendaten
    -1.30
     protoimpl
    -1.27
    POSITIVE LOGITS
     
    0.57
    …
    0.56
     the
    0.54
    ...
    0.54
    ,
    0.51
     C
    0.51
     a
    0.51
    <eos>
    0.51
     in
    0.50
     on
    0.50
    Activations Density 0.218%

    No Known Activations