© 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. 28-GEMMASCOPE-RES-16K
    6. 3913
    Prev
    Next
    INDEX
    Explanations

    elements related to connectivity and functionality in technology and engineering contexts

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

    Prepositions (in, to, for, with)

    np_acts-logits-general · gemini-2.0-flash

    in accordance with, in dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.57
     تكبرها
    -0.53
     يتيمه
    -0.49
     casó
    -0.49
    tagHelperRunner
    -0.49
    httphttps
    -0.49
     zijne
    -0.46
    nezeu
    -0.45
     transfieras
    -0.44
    calips
    -0.44
    POSITIVE LOGITS
    transQ
    0.54
    IVEREF
    0.44
     awakeFromNib
    0.43
    GTCX
    0.40
     by
    0.40
     oleh
    0.40
     quite
    0.38
    atelyn
    0.38
    quite
    0.36
     ویکی‌پدی
    0.36
    Activations Density 1.290%

    No Known Activations