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. 0-GEMMASCOPE-RES-16K
    6. 321
    Prev
    Next
    INDEX
    Explanations

    references to tanks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ru
    -0.69
    j
    -0.64
    he
    -0.62
    -
    -0.60
    f
    -0.59
    V
    -0.58
    ti
    -0.58
    rd
    -0.58
    _
    -0.57
    v
    -0.56
    POSITIVE LOGITS
     Roskov
    1.26
    tagHelperRunner
    1.23
     protoimpl
    1.18
    BufferException
    1.17
     Efq
    1.12
    Personendaten
    1.06
    DockStyle
    1.06
     propOrder
    1.06
    LookAnd
    1.04
     $_"
    1.03
    Activations Density 0.190%

    No Known Activations