Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14-GEMMASCOPE-RES-16K
    6. 12919
    Prev
    Next
    INDEX
    Explanations

    legal terminology and case citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Signalez
    -1.48
    NameInMap
    -1.11
     <=",
    -1.08
    yntaxException
    -1.08
     мәкал
    -1.06
    TypedDataSet
    -1.06
    Personendaten
    -1.05
    IVEREF
    -1.05
    ConstraintMaker
    -1.03
     '\\;'
    -1.03
    POSITIVE LOGITS
    CodeDom
    0.95
     
    0.59
    </strong>
    0.57
     an
    0.47
    </em>
    0.46
     la
    0.45
     A
    0.42
    <strong>
    0.42
     chi
    0.41
     source
    0.41
    Activations Density 0.003%

    No Known Activations