© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1337
    Prev
    Next
    INDEX
    Explanations

    the start of new sections or topics within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FieldDescriptor
    -0.59
    apimachinery
    -0.58
    paramref
    -0.54
     انگلیسی
    -0.54
    itinéraire
    -0.53
     ddelweddau
    -0.53
    PyExc
    -0.52
    nologue
    -0.52
    GeneratedCode
    -0.51
     पास
    -0.49
    POSITIVE LOGITS
    NUMX
    0.64
     ☐
    0.61
     ③
    0.56
     nephe
    0.56
    wußt
    0.55
     doubtnut
    0.55
     Madi
    0.53
    anskje
    0.53
    \<^
    0.53
     XNUMX
    0.53
    Activations Density 0.315%

    No Known Activations