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. 16-GEMMASCOPE-RES-16K
    6. 2879
    Prev
    Next
    INDEX
    Explanations

    references to specific identifiers or names in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     a
    -0.64
     the
    -0.58
    ,
    -0.55
     in
    -0.55
     (
    -0.53
    .
    -0.53
     or
    -0.51
    </h2>
    -0.51
     of
    -0.51
     and
    -0.49
    POSITIVE LOGITS
    ècie
    0.98
    setVerticalGroup
    0.97
    \{\\
    0.87
     Beſ
    0.87
     Monfieur
    0.87
    ########.
    0.87
     estekak
    0.86
     Administrativna
    0.85
     ARXIV
    0.84
     saveiro
    0.83
    Activations Density 0.305%

    No Known Activations