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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 3806
    Prev
    Next
    INDEX
    Explanations

    references to locations or spatial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AxisAlignment
    -0.60
    inor
    -0.57
     StringTokenizer
    -0.57
    beforeEach
    -0.54
     venit
    -0.53
     luat
    -0.53
    EnumMember
    -0.52
     chambers
    -0.50
    createForm
    -0.49
     ventricular
    -0.48
    POSITIVE LOGITS
     sobre
    1.55
     върху
    1.44
    sobre
    1.28
     sulla
    1.22
     sulle
    1.22
     على
    1.19
     sull
    1.16
     asupra
    1.14
     Sobre
    1.12
     SOBRE
    1.12
    Activations Density 0.229%

    No Known Activations